Foundation Models & Evaluations
AI Benchmark Leaderboard & Model Rankings
Empirical, contamination-audited evaluations across LiveBench, Artificial Analysis intelligence indices, generation speed, context windows, and real API pricing for 699 foundation models.
699 ModelsFrontier, Flagship & Open Weights
64 BenchmarksAudited & Contamination Checked
Speed & LatencyReal-World Tokens/Sec Telemetry
Token EconomicsStandardized $/1M Tokens
LiveBench Contamination-Resistant Suite: Hard questions updated periodically with strict test-set isolation to prevent pre-training data memorization.
| Rank | Model & Lab | Global Avg | Reasoning | Coding | Math | Data | IF | Throughput | Pricing / 1M |
|---|---|---|---|---|---|---|---|---|---|
| #1 | GPT-6.1 Sol Pro OpenAIFrontier | 84.8% | — | — | — | — | — | 58 tok/s | $6.00/$30.00 |
| #2 | Claude Fable 5.1 AnthropicFrontier | 84.7% | 89.7% | 86.4% | 88.5% | 82.1% | 81.3% | 54 tok/s | $5.00/$25.00 |
| #3 | GPT-6 Astra OpenAIFrontier | 84.2% | 91.7% | 85.9% | 90.2% | 81.4% | 78.0% | 62 tok/s | $4.50/$20.00 |
| #4 | Gemini 4 Argon Google DeepMindFrontier | 84.1% | — | — | — | — | — | 90 tok/s | $2.50/$10.00 |
| #5 | DeepSeek V4.1 Flash DeepSeekOpen | 83.9% | 88.4% | 85.1% | 89.0% | 80.5% | 82.0% | 96 tok/s | $0.18/$0.55 |
| #6 | Claude Opus 5.5 AnthropicFrontier | 83.5% | — | — | — | — | — | 52 tok/s | $15.00/$75.00 |
| #7 | Muse Wonder Full Meta AIFrontier | 83.5% | — | — | — | — | — | 65 tok/s | $4.50/$18.00 |
| #8 | Claude Fable 5 AnthropicFrontier | 83.0% | 89.7% | 86.0% | 96.0% | 81.2% | 70.0% | 45 tok/s | $10.00/$50.00 |
| #9 | GPT-5.6 Sol OpenAIFrontier | 82.8% | 88.0% | 84.1% | 87.5% | 80.1% | 80.0% | 62 tok/s | $5.00/$30.00 |
| #10 | o3 OpenAIFrontier | 82.5% | 89.5% | 84.0% | 88.9% | 79.5% | 77.2% | 68 tok/s | $4.00/$18.00 |
| #11 | Claude Sonnet 5.5 AnthropicFrontier | 82.0% | — | — | — | — | — | 105 tok/s | $3.00/$15.00 |
| #12 | GPT-5 OpenAIFrontier | 82.0% | 94.8% | 84.5% | 94.0% | 88.5% | 95.5% | 85 tok/s | $2.50/$10.00 |
| #13 | Kimi K3 Moonshot AIOpen | 82.0% | 90.7% | 83.5% | 87.0% | 79.0% | 76.0% | 58 tok/s | $2.80/$14.00 |
| #14 | Space Bunny Alpha Stealth AI ResearchFrontier | 81.8% | — | — | — | — | — | 110 tok/s | $1.50/$6.00 |
| #16 | GPT-6 Luna OpenAIFrontier | 81.5% | — | — | — | — | — | 120 tok/s | $2.00/$8.00 |
| #15 | Claude 3.7 Sonnet AnthropicFrontier | 81.5% | 86.8% | 83.2% | 86.4% | 79.2% | 77.0% | 72 tok/s | $3.00/$15.00 |
| #17 | OpenAI Decisions API OpenAIFrontier | 81.5% | — | — | — | — | — | 320 tok/s | $0.35/$0.70 |
| #19 | Grok 4 xAIFrontier | 81.2% | 94.5% | 84.0% | 95.0% | 87.0% | 94.0% | 75 tok/s | $5.00/$20.00 |
| #18 | Grok 3 xAIFrontier | 81.2% | 87.0% | 82.5% | 86.2% | 78.0% | 76.5% | 80 tok/s | $3.00/$15.00 |
| #20 | Gemini 2.5 Pro Google DeepMindFrontier | 81.0% | 86.5% | 82.0% | 86.0% | 78.5% | 77.0% | 85 tok/s | $1.25/$5.00 |
| #22 | Muse Wonder Meta AIFrontier | 80.8% | — | — | — | — | — | 85 tok/s | $1.80/$7.20 |
| #21 | DeepSeek-R1 DeepSeekOpen | 80.8% | 87.9% | 81.5% | 87.2% | 78.0% | 75.2% | 65 tok/s | $0.55/$2.19 |
| #67 | Qwen: Qwen3.8 Max Prime Alibaba Cloud / QwenOpen | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $4.00/$12.00 |
| #32 | Claude Opus 5.5 AnthropicFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $4.00/$20.00 |
| #59 | GPT-6 Astra Pro OpenAIFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $10.00/$50.00 |
| #31 | Claude Opus 5 AnthropicFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $5.00/$25.00 |
| #57 | GPT-5.6 Terra Pro OpenAIFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $2.00/$12.00 |
| #55 | GPT-5.6 Sol Pro OpenAIFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $4.00/$20.00 |
| #30 | Claude Opus 4.8 AnthropicFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $5.00/$25.00 |
| #35 | Gemini 3 Pro Image (Nano Banana Pro) Google DeepMindFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $2.00/$12.00 |
| #53 | GPT-5.5 Pro OpenAIFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $30.00/$180.00 |
| #29 | Claude Opus 4.7 AnthropicFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $5.00/$25.00 |
| #51 | GPT-5.4 Pro OpenAIFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $30.00/$180.00 |
| #38 | Gemini 3.1 Pro Custom Tools Google DeepMindFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $2.00/$12.00 |
| #37 | Gemini 3.1 Pro Google DeepMindFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $2.00/$12.00 |
| #28 | Claude Opus 4.6 AnthropicFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $5.00/$25.00 |
| #46 | GPT-5.2 Pro OpenAIFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $21.00/$168.00 |
| #27 | Claude Opus 4.5 AnthropicFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $5.00/$25.00 |
| #36 | Gemini 3 Pro Image (Nano Banana Pro) Google DeepMindFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $2.00/$12.00 |
| #43 | GPT-5 Pro OpenAIFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $15.00/$120.00 |
| #24 | Claude 4.1 Opus AnthropicFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $15.00/$75.00 |
| #64 | o3 Pro OpenAIFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $20.00/$80.00 |
| #66 | Perplexity: Sonar Pro Search Perplexity AIFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $3.00/$15.00 |
| #65 | Perplexity: Sonar Pro Perplexity AIFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $3.00/$15.00 |
| #63 | o1-pro OpenAIFrontier | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $150.00/$600.00 |
| #68 | Sonar Reasoning Pro Perplexity AIFrontier | 80.5% | 87.0% | 81.2% | 86.0% | 78.0% | 75.2% | 78 tok/s | $2.00/$8.00 |
| #61 | Muse Wonder Meta AIOpen | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $4.00/$20.00 |
| #58 | GPT-6 Astra OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $10.00/$50.00 |
| #26 | Claude Fable 5.1 Anthropic | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $10.00/$50.00 |
| #60 | MoonshotAI: Kimi K3 Moonshot AI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $0.19/$15.00 |
| #56 | GPT-5.6 Terra OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $2.00/$12.00 |
| #54 | GPT-5.6 Sol OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $4.00/$20.00 |
| #25 | Claude Fable 5 Anthropic | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $10.00/$50.00 |
| #39 | GPT Chat Latest OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $5.00/$30.00 |
| #52 | GPT-5.5 OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $5.00/$30.00 |
| #50 | GPT-5.4 Image 2 OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $8.00/$15.00 |
| #49 | GPT-5.4 OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $2.50/$15.00 |
| #48 | GPT-5.3-Codex OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $1.75/$14.00 |
| #34 | Claude Sonnet 4.6 Anthropic | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $3.00/$15.00 |
| #47 | GPT-5.2-Codex OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $1.75/$14.00 |
| #45 | GPT-5.2 Chat OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $1.75/$14.00 |
| #44 | GPT-5.2 OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $1.75/$14.00 |
| #33 | Claude Sonnet 4.5 Anthropic | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $3.00/$15.00 |
| #23 | Amazon: Nova Premier 1.0 Amazon AWS Bedrock | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $2.50/$12.50 |
| #62 | o1 OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $15.00/$60.00 |
| #42 | GPT-4o OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $5.00/$15.00 |
| #41 | GPT-4 Turbo OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $10.00/$30.00 |
| #40 | GPT-4 OpenAI | 80.5% | 84.2% | 82.4% | 81.4% | 77.8% | 80.5% | 55 tok/s | $30.00/$60.00 |
| #69 | Claude Sonnet 5 AnthropicFrontier | 80.4% | 93.0% | 83.2% | 91.5% | 86.5% | 94.8% | 95 tok/s | $3.00/$15.00 |
| #71 | GPT-5.5 Thinking OpenAIFrontier | 80.2% | 89.7% | 82.1% | 95.9% | 78.4% | 68.0% | 70 tok/s | $3.00/$15.00 |
| #70 | Gemini 3.8 Flash Google DeepMindFrontier | 80.2% | — | — | — | — | — | 185 tok/s | $0.75/$3.75 |
| #72 | o3-mini OpenAIFrontier | 80.2% | 87.2% | 81.0% | 86.5% | 77.0% | 75.0% | 115 tok/s | $1.10/$4.40 |
| #73 | Claude Opus 5 AnthropicFrontier | 80.1% | 91.2% | 81.4% | 95.7% | 78.0% | 67.5% | 48 tok/s | $5.00/$25.00 |
| #75 | Qwen 3.8 Max Prime Alibaba Cloud / QwenOpen | 80.0% | — | — | — | — | — | 68 tok/s | $0.90/$2.70 |
| #74 | Ollama DeepSeek-R1 (Q4_K_M) Ollama (Inference Runtime)Open | 80.0% | — | — | — | — | — | 24 tok/s | $0.55/$2.19 |
| #77 | Gemini 3 Pro Google DeepMindFrontier | 79.8% | 92.0% | 81.5% | 92.0% | 88.0% | 93.5% | 80 tok/s | $2.50/$10.00 |
| #76 | Gemini 2.5 Flash (Thinking) Google DeepMind | 79.8% | 85.2% | 80.5% | 84.8% | 76.5% | 77.0% | 145 tok/s | $0.07/$0.30 |
| #78 | Jev 1.14 TypeSafe AIFrontier | 79.4% | — | — | — | — | — | 290 tok/s | $0.25/$0.50 |
| #79 | QwQ-32B Alibaba Cloud / Qwen | 79.2% | 86.0% | 80.0% | 85.5% | 76.0% | 75.0% | — | $0.20/$0.60 |
| #80 | Gemini 3.7 Flash Google DeepMindFrontier | 78.8% | 87.8% | 78.9% | 93.5% | 76.5% | 65.9% | 182 tok/s | $0.75/$3.75 |
| #84 | Grok 4.6 xAIFrontier | 78.5% | 88.4% | 80.2% | 92.1% | 75.8% | 65.1% | 75 tok/s | $2.00/$6.00 |
| #83 | GLM 5.3 Flash Zhipu AI (Z.ai)Open | 78.5% | — | — | — | — | — | 130 tok/s | $0.20/$0.80 |
| #85 | Nemotron 3 Ultra 550B NVIDIA AI & NIMOpen | 78.5% | — | — | — | — | — | 85 tok/s | $0.45/$1.80 |
| #82 | Claude Haiku 5.5 Anthropic | 78.5% | — | — | — | — | — | 160 tok/s | $1.00/$5.00 |
| #81 | Claude 3.5 Sonnet (v2) Anthropic | 78.5% | 83.5% | 79.2% | 82.0% | 76.0% | 75.0% | — | $3.00/$15.00 |
| #86 | Sarvam 105B Sarvam AIFrontier | 78.4% | — | — | — | — | — | 72 tok/s | $1.20/$3.60 |
| #87 | Amazon Nova Premier 1.0 Amazon AWS BedrockFrontier | 78.2% | — | — | — | — | — | 72 tok/s | $2.00/$8.00 |
| #88 | Jev TypeSafe AIFrontier | 78.0% | — | — | — | — | — | 280 tok/s | $0.20/$0.40 |
| #94 | DeepSeek V4-Pro DeepSeekOpen | 77.9% | 87.1% | 81.0% | 91.4% | 75.2% | 64.8% | 65 tok/s | $0.66/$1.98 |
| #119 | GPT-6.1 Terra Pro OpenAIFrontier | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.00/$5.00 |
| #125 | MoonshotAI: Kimi K3.1 Pro Moonshot AIFrontier | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$10.00 |
| #117 | GPT-6.1 Sol Pro OpenAIFrontier | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$10.00 |
| #115 | GPT-6 Sol Pro OpenAIFrontier | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$10.00 |
| #151 | Z.ai: GLM 5.3 Prime Zhipu AI (Z.ai)Open | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.80/$8.80 |
| #146 | Xiaomi: MiMo-V2.6-Pro-UltraSpeed XiaomiOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $4.35/$8.70 |
| #142 | Qwen: Qwen3.8 Max (0902) Alibaba Cloud / QwenOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$6.00 |
| #140 | Qwen: Qwen3.7 Max Alibaba Cloud / QwenOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.48/$4.42 |
| #93 | DeepSeek V4 Pro 0423 DeepSeekOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.60/$3.20 |
| #112 | GPT-5.1-Codex-Max OpenAIFrontier | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $1.25/$10.00 |
| #95 | Gemini 2.5 Pro Google DeepMindFrontier | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $1.25/$10.00 |
| #96 | Gemini 2.5 Pro 06-05 Google DeepMindFrontier | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $1.25/$10.00 |
| #137 | Perplexity: Sonar Reasoning Pro Perplexity AIFrontier | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$8.00 |
| #89 | Amazon: Nova Pro 1.0 Amazon AWS BedrockFrontier | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $0.80/$3.20 |
| #120 | Mistral Large Mistral AIOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$6.00 |
| #118 | GPT-6.1 Terra OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.00/$5.00 |
| #129 | Muse Spark Open Meta AIOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.25/$4.25 |
| #101 | Gemini 4 Argon Google DeepMind | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$10.00 |
| #130 | Nano Banana 2.1 Google DeepMind | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $1.50/$7.50 |
| #116 | GPT-6.1 Sol OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$10.00 |
| #92 | Claude Sonnet 5.5 Anthropic | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$10.00 |
| #114 | GPT-6 Sol OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$10.00 |
| #145 | SpaceXAI: Grok 4.7 xAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$6.00 |
| #100 | Gemini 3.8 Flash Google DeepMind | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $0.82/$4.13 |
| #128 | Muse Spark 1.3 Meta AIOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.25/$4.25 |
| #99 | Gemini 3.7 Flash Google DeepMind | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $0.75/$3.75 |
| #141 | Qwen: Qwen3.8 2.4T A95B Alibaba Cloud / QwenOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$6.00 |
| #144 | SpaceXAI: Grok 4.6 xAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$6.00 |
| #127 | Muse Spark 1.2 Meta AIOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.25/$4.25 |
| #98 | Gemini 3.6 Flash Google DeepMind | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $0.75/$3.75 |
| #126 | Muse Spark 1.1 Meta AIOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.25/$4.25 |
| #143 | SpaceXAI: Grok 4.5 xAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$6.00 |
| #91 | Claude Sonnet 5 Anthropic | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$10.00 |
| #150 | Z.ai: GLM 5.2 Zhipu AI (Z.ai)Open | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $0.01/$6.80 |
| #124 | MoonshotAI: Kimi K2.7 Code Moonshot AI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $0.60/$3.50 |
| #97 | Gemini 3.5 Flash Google DeepMind | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $1.50/$9.00 |
| #121 | Mistral Medium 3.5 Mistral AIOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $1.50/$7.50 |
| #123 | MoonshotAI: Kimi K2.6 Moonshot AI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $0.65/$3.41 |
| #149 | Z.ai: GLM 5.1 Zhipu AI (Z.ai)Open | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.40/$4.40 |
| #152 | Z.ai: GLM 5V Turbo Zhipu AI (Z.ai)Open | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.20/$4.00 |
| #113 | GPT-5.4 Mini OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $0.75/$4.50 |
| #148 | Z.ai: GLM 5 Turbo Zhipu AI (Z.ai)Open | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.20/$4.00 |
| #139 | Qwen: Qwen3.5 397B A17B Alibaba Cloud / QwenOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $0.50/$3.60 |
| #147 | Z.ai: GLM 5 Zhipu AI (Z.ai)Open | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.00/$3.20 |
| #102 | GPT Audio OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.50/$10.00 |
| #110 | GPT-5.1 OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $1.25/$10.00 |
| #111 | GPT-5.1-Codex OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $1.25/$10.00 |
| #109 | GPT-5 Image OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $10.00/$10.00 |
| #90 | Claude Haiku 4.5 Anthropic | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.00/$5.00 |
| #108 | GPT-5 OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $1.25/$10.00 |
| #138 | Qwen: Qwen3 235B A22B Thinking 2507 Alibaba Cloud / QwenOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $0.45/$3.50 |
| #135 | o4 Mini High OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.10/$4.40 |
| #131 | o3 OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$8.00 |
| #134 | o4 Mini OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.10/$4.40 |
| #136 | Perplexity: Sonar Deep Research Perplexity AI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$8.00 |
| #133 | o3 Mini High OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.10/$4.40 |
| #132 | o3 Mini OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $1.10/$4.40 |
| #105 | GPT-4o OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.50/$10.00 |
| #106 | GPT-4o OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.50/$10.00 |
| #107 | GPT-4o OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.50/$10.00 |
| #122 | Mixtral 8x22B Instruct Mistral AIOpen | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$6.00 |
| #103 | GPT-3.5 Turbo 16k OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 85 tok/s | $3.00/$4.00 |
| #104 | GPT-4.1 OpenAI | 77.9% | 81.4% | 79.7% | 78.8% | 75.2% | 77.9% | 55 tok/s | $2.00/$8.00 |
| #153 | Qwen3-235B Alibaba Cloud / QwenOpen | 77.4% | 87.5% | 80.5% | 91.0% | 74.8% | 64.0% | 70 tok/s | $0.80/$2.40 |
| #154 | Gemini 3.6 Flash Google DeepMindFrontier | 77.2% | 86.5% | 77.8% | 91.2% | 75.0% | 64.5% | 175 tok/s | $0.75/$3.75 |
| #155 | Microsoft-Decision-1 Microsoft Research & AzureOpen | 77.2% | — | — | — | — | — | 240 tok/s | $0.08/$0.16 |
| #156 | Llama 4 Maverick Meta AIOpen | 77.1% | 88.2% | 79.0% | 89.5% | 82.0% | 90.0% | 82 tok/s | $0.50/$1.50 |
| #157 | GLM-5.2 Zhipu AI (Z.ai)Frontier | 77.0% | 86.8% | 79.5% | 90.5% | 76.0% | 66.0% | 72 tok/s | $1.50/$6.00 |
| #158 | Sonar Pro Perplexity AI | 77.0% | 81.5% | 76.5% | 80.0% | 74.5% | 75.5% | 85 tok/s | $1.00/$1.00 |
| #159 | MiniMax M3 MiniMaxFrontier | 76.8% | — | — | — | — | — | 88 tok/s | $0.30/$1.20 |
| #162 | QwQ Plus Alibaba Cloud / QwenOpen | 76.5% | 88.0% | 79.0% | 92.5% | 74.0% | 63.0% | 52 tok/s | $0.80/$2.40 |
| #161 | Qwen 2.5 72B Instruct Alibaba Cloud / QwenOpen | 76.5% | 81.0% | 77.0% | 81.5% | 74.0% | 72.0% | 82 tok/s | $0.35/$0.70 |
| #160 | Phi-4 Microsoft Research & AzureOpen | 76.5% | — | — | — | — | — | 105 tok/s | $0.07/$0.14 |
| #163 | Gemma 3 27B Google DeepMindOpen | 76.2% | 80.5% | 75.8% | 79.8% | 74.2% | 74.0% | 88 tok/s | $0.25/$0.50 |
| #164 | Llama 4 Scout Meta AIOpen | 76.0% | 87.0% | 77.5% | 87.0% | 80.0% | 89.0% | 140 tok/s | $0.20/$0.60 |
| #165 | Krutrim-2 Krutrim AIFrontier | 75.8% | — | — | — | — | — | 85 tok/s | $0.15/$0.45 |
| #166 | Llama 3.3 70B Instruct Meta AI | 75.8% | 80.5% | 75.5% | 79.5% | 73.5% | 72.5% | 90 tok/s | $0.30/$0.60 |
| #167 | Llama-3.1-Nemotron-70B-Instruct NVIDIA AI & NIMOpen | 75.4% | — | — | — | — | — | 78 tok/s | $0.35/$0.40 |
| #168 | Mistral Large 2 Mistral AI | 75.2% | 79.8% | 75.0% | 78.5% | 73.0% | 72.0% | — | $2.00/$6.00 |
| #170 | Ollama Llama 3.3 (Q4_K_M) Ollama (Inference Runtime)Open | 75.0% | — | — | — | — | — | 42 tok/s | $0.60/$1.20 |
| #169 | Grok 3 Mini xAI | 75.0% | — | — | — | — | — | 190 tok/s | $0.30/$1.20 |
| #171 | Gemini 2.0 Flash Thinking Google DeepMindFrontier | 74.9% | 87.0% | 75.2% | 88.5% | 79.0% | 89.0% | 95 tok/s | $0.10/$0.40 |
| #179 | DeepSeek V4 Pro 0813 DeepSeekOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.66/$1.98 |
| #200 | GPT-5.6 Luna Pro OpenAIFrontier | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.20/$1.20 |
| #199 | GPT-5.6 Luna OpenAIFrontier | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.20/$1.20 |
| #220 | Nemotron 3 Ultra NVIDIA AI & NIMOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.60/$2.40 |
| #208 | MiniMax: MiniMax M3 MiniMaxFrontier | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.30/$1.20 |
| #238 | Xiaomi: MiMo-V2.5-Pro XiaomiOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.48/$1.80 |
| #207 | MiniMax: MiniMax M2.7 MiniMaxFrontier | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.30/$1.20 |
| #205 | MiniMax: MiniMax M2-her MiniMaxFrontier | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.30/$1.20 |
| #206 | MiniMax: MiniMax M2.1 MiniMaxFrontier | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.30/$1.20 |
| #204 | MiniMax: MiniMax M2 MiniMaxFrontier | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.26/$1.02 |
| #203 | MiniMax: MiniMax M1 MiniMaxFrontier | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.55/$2.20 |
| #209 | MiniMax: MiniMax-01 MiniMaxFrontier | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.20/$1.10 |
| #211 | Mistral Large 4 Mistral AIOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.70/$2.10 |
| #210 | Mistral Large 3 2512 Mistral AIOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.50/$1.50 |
| #201 | Hunyuan-Large TencentOpen | 74.8% | — | — | — | — | — | 65 tok/s | $0.60/$1.80 |
| #244 | Z.ai: GLM 5.3 FlashX Zhipu AI (Z.ai)Open | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.37/$1.25 |
| #202 | Hy4 TencentOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.83/$2.50 |
| #243 | Z.ai: GLM 5.3 Zhipu AI (Z.ai)Open | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.07/$1.40 |
| #231 | Qwen: Qwen3.8 27B Alibaba Cloud / QwenOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.04/$2.30 |
| #218 | Muse Glimmer 30B Meta AIOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.30/$1.20 |
| #173 | ByteDance Seed: Seed 2.1 Turbo ByteDance Research | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.50/$2.50 |
| #174 | ByteDance Seed: Seed-2.0-Code ByteDance Research | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.50/$3.00 |
| #189 | Gemini 3.5 Flash Lite Google DeepMind | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.30/$2.50 |
| #188 | Gemini 3.1 Flash Lite Image Google DeepMind | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.25/$1.50 |
| #230 | Qwen: Qwen3.7 Plus Alibaba Cloud / QwenOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.32/$1.28 |
| #184 | Gemini 3.1 Flash Image Google DeepMind | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.50/$3.00 |
| #236 | SpaceXAI: Grok Build 0.1 xAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $1.00/$2.00 |
| #186 | Gemini 3.1 Flash Lite Google DeepMind | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.25/$1.50 |
| #235 | SpaceXAI: Grok 4.3 xAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $1.25/$2.50 |
| #228 | Qwen: Qwen3.6 Flash Alibaba Cloud / QwenOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.19/$1.13 |
| #227 | Qwen: Qwen3.6 27B Alibaba Cloud / QwenOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.45/$2.70 |
| #237 | Xiaomi: MiMo-V2.5 XiaomiOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.40/$2.00 |
| #224 | Qwen: Qwen3.5 Plus 2026-04-20 Alibaba Cloud / QwenOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.30/$1.80 |
| #229 | Qwen: Qwen3.6 Plus Alibaba Cloud / QwenOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.33/$1.95 |
| #198 | GPT-5.4 Nano OpenAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.20/$1.25 |
| #234 | SpaceXAI: Grok 4.20 Multi-Agent xAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $1.25/$2.50 |
| #233 | SpaceXAI: Grok 4.20 xAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $1.25/$2.50 |
| #175 | ByteDance Seed: Seed-2.0-Lite ByteDance Research | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.25/$2.00 |
| #187 | Gemini 3.1 Flash Lite Google DeepMind | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.25/$1.50 |
| #185 | Gemini 3.1 Flash Image Google DeepMind | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.50/$3.00 |
| #226 | Qwen: Qwen3.5-27B Alibaba Cloud / QwenOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.26/$2.60 |
| #225 | Qwen: Qwen3.5-122B-A10B Alibaba Cloud / QwenOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.26/$2.08 |
| #223 | Qwen: Qwen3.5 Plus 2026-02-15 Alibaba Cloud / QwenOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.26/$1.56 |
| #217 | MoonshotAI: Kimi K2.5 Moonshot AI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.50/$2.50 |
| #190 | GPT Audio Mini OpenAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.60/$2.40 |
| #183 | Gemini 3 Flash Google DeepMind | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.50/$3.00 |
| #180 | Devstral 2 2512 Mistral AIOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.40/$2.00 |
| #197 | GPT-5.1-Codex-Mini OpenAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.25/$2.00 |
| #216 | MoonshotAI: Kimi K2 Thinking Moonshot AI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.60/$2.50 |
| #195 | GPT-5 Image Mini OpenAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $2.50/$2.00 |
| #222 | Qwen: Qwen3 VL 235B A22B Instruct Alibaba Cloud / QwenOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.21/$1.90 |
| #221 | Qwen: Qwen3 Next 80B A3B Instruct Alibaba Cloud / QwenOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.09/$1.10 |
| #215 | MoonshotAI: Kimi K2 0905 Moonshot AI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.60/$2.50 |
| #213 | Mistral Medium 3.1 Mistral AIOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.40/$2.00 |
| #196 | GPT-5 Mini OpenAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.25/$2.00 |
| #214 | MoonshotAI: Kimi K2 0711 Moonshot AI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.57/$2.30 |
| #172 | ByteDance Seed: Seed 1.6 ByteDance Research | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.25/$2.00 |
| #212 | Mistral Medium 3 Mistral AIOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.40/$2.00 |
| #182 | Gemini 2.5 Flash Image Google DeepMind | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.30/$2.50 |
| #181 | Gemini 2.5 Flash Google DeepMind | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.30/$2.50 |
| #176 | Command A+ Cohere | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.30/$1.50 |
| #232 | R1 0528 DeepSeekOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.50/$2.15 |
| #178 | DeepSeek V3 0324 DeepSeekOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.29/$1.14 |
| #177 | DeepSeek V3 DeepSeekOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.26/$1.03 |
| #242 | Z.ai: GLM 4.7 Zhipu AI (Z.ai)Open | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.54/$1.98 |
| #241 | Z.ai: GLM 4.6 Zhipu AI (Z.ai)Open | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.50/$2.00 |
| #240 | Z.ai: GLM 4.5V Zhipu AI (Z.ai)Open | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.60/$1.80 |
| #239 | Z.ai: GLM 4.5 Zhipu AI (Z.ai)Open | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.60/$2.20 |
| #192 | GPT-3.5 Turbo (older v0613) OpenAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $1.00/$2.00 |
| #194 | GPT-4.1 Mini OpenAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.40/$1.60 |
| #219 | Nemotron 3 Super NVIDIA AI & NIMOpen | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.30/$2.40 |
| #193 | GPT-3.5 Turbo Instruct OpenAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $1.50/$2.00 |
| #191 | GPT-3.5 Turbo OpenAI | 74.8% | 78.2% | 76.5% | 75.7% | 72.3% | 74.8% | 85 tok/s | $0.50/$1.50 |
| #245 | DeepSeek V4-Flash DeepSeekOpen | 74.5% | 84.0% | 75.5% | 86.0% | 72.0% | 62.0% | 190 tok/s | $0.14/$0.28 |
| #246 | Nemotron-4-340B-Reward NVIDIA AI & NIMOpen | 74.5% | — | — | — | — | — | 45 tok/s | $1.20/$1.20 |
| #248 | Nemotron 3 Super 120B NVIDIA AI & NIMOpen | 74.2% | — | — | — | — | — | 130 tok/s | $0.15/$0.60 |
| #247 | Amazon Nova Pro Amazon AWS Bedrock | 74.2% | — | — | — | — | — | 120 tok/s | $0.80/$3.20 |
| #249 | Amazon Nova Pro 1.0 Amazon AWS Bedrock | 74.0% | — | — | — | — | — | 88 tok/s | $0.80/$3.20 |
| #250 | Sarvam 30B Sarvam AI | 74.0% | — | — | — | — | — | 95 tok/s | $0.25/$0.75 |
| #251 | Sonar Perplexity AI | 74.0% | 78.0% | 73.0% | 76.5% | 71.5% | 73.0% | 92 tok/s | $0.50/$0.50 |
| #252 | Gemini 3.5 Flash-Lite Google DeepMind | 73.8% | 83.5% | 74.0% | 85.2% | 71.0% | 61.5% | 220 tok/s | $0.10/$0.40 |
| #253 | QwQ 32B Alibaba Cloud / QwenOpen | 73.8% | 86.2% | 74.8% | 89.1% | 75.2% | 85.0% | 45 tok/s | $0.20/$0.60 |
| #254 | o1 OpenAIFrontier | 73.5% | 86.8% | 74.0% | 89.2% | 77.0% | 87.5% | 45 tok/s | $15.00/$60.00 |
| #255 | Yi-Lightning 01.AI | 73.5% | — | — | — | — | — | 110 tok/s | $0.14/$0.14 |
| #256 | Sarvam Vision (Document AI) Sarvam AI | 73.2% | — | — | — | — | — | 88 tok/s | $0.40/$1.20 |
| #258 | Nemotron-4-340B-Instruct NVIDIA AI & NIMOpen | 73.0% | — | — | — | — | — | 42 tok/s | $1.20/$1.20 |
| #257 | MiniMax-Text-01 MiniMax | 73.0% | — | — | — | — | — | 75 tok/s | $0.20/$1.10 |
| #260 | Gemini 2.0 Pro Google DeepMindFrontier | 72.8% | 85.5% | 73.5% | 85.0% | 80.1% | 88.0% | 60 tok/s | $1.50/$6.00 |
| #259 | Amazon Nova 2 Lite Amazon AWS Bedrock | 72.8% | — | — | — | — | — | 175 tok/s | $0.08/$0.32 |
| #262 | Krutrim Pro Krutrim AI | 72.5% | — | — | — | — | — | 98 tok/s | $0.10/$0.30 |
| #261 | GLM-4-Plus Zhipu AI (Z.ai) | 72.5% | — | — | — | — | — | 65 tok/s | $1.40/$1.40 |
| #263 | Mistral Large 3 Mistral AI | 72.0% | 85.0% | 73.0% | 84.0% | 78.0% | 88.0% | 60 tok/s | $2.00/$6.00 |
| #264 | Phi-4-multimodal Microsoft Research & AzureOpen | 72.0% | — | — | — | — | — | 140 tok/s | $0.05/$0.10 |
| #265 | ERNIE 4.0 Turbo Baidu | 71.8% | — | — | — | — | — | 58 tok/s | $4.20/$8.40 |
| #268 | WizardLM-2 8x22B Microsoft Research & AzureOpen | 71.5% | — | — | — | — | — | 68 tok/s | $0.50/$0.50 |
| #266 | Gemma 2 27B Google DeepMindOpen | 71.5% | 74.5% | 69.5% | 73.0% | 70.0% | 71.0% | 95 tok/s | $0.20/$0.40 |
| #267 | Saaras v3 (Speech-to-Text) Sarvam AI | 71.5% | — | — | — | — | — | 180 tok/s | $0.10/$0.30 |
| #269 | Qwen 2.5 Max Alibaba Cloud / Qwen | 71.4% | 84.5% | 71.5% | 83.0% | 76.5% | 87.0% | 58 tok/s | $1.60/$6.40 |
| #311 | MiniMax: MiniMax M3.1 Flash MiniMaxFrontier | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.15/$0.60 |
| #294 | GPT-6 Luna Pro OpenAIFrontier | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.10/$0.50 |
| #293 | GPT-6 Luna OpenAIFrontier | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.10/$0.50 |
| #343 | Xiaomi: MiMo-V2.6-Pro XiaomiOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.43/$0.87 |
| #310 | MiniMax: MiniMax M2.5 MiniMaxFrontier | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.27/$0.95 |
| #340 | Upstage: Solar Pro 4 UpstageFrontier | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.15/$0.60 |
| #283 | DeepSeek V4.1 Flash 1017 DeepSeekOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.15/$0.60 |
| #315 | Nemotron 3.5 Super VL NVIDIA AI & NIMOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.15/$0.50 |
| #303 | LiquidAI: LFM2.5-24B-A2B Liquid AI | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.05/$0.70 |
| #273 | Claude Haiku 5.5 Anthropic | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.10/$0.50 |
| #342 | Xiaomi: MiMo-V2.6-Flash XiaomiOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.14/$0.28 |
| #336 | Qwen: Qwen3.8 Omni Flash Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.15/$0.47 |
| #282 | DeepSeek V4.1 Flash DeepSeekOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.04/$0.50 |
| #335 | Qwen: Qwen3.8 Flash Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.15/$0.47 |
| #281 | DeepSeek V4 Flash Vision Exp DeepSeekOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.22/$0.65 |
| #302 | LiquidAI: LFM2.5-2.6B Liquid AI | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.35/$0.50 |
| #280 | DeepSeek V4 Flash 0731 DeepSeekOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.12/$0.24 |
| #300 | Hy3 TencentOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.13/$0.53 |
| #298 | Hy-MT2-30B-A3B TencentOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.07/$0.29 |
| #299 | Hy-MT2-7B TencentOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.07/$0.29 |
| #301 | Hy3 TencentOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.18/$0.60 |
| #334 | Qwen: Qwen3.6 35B A3B Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.10/$0.90 |
| #287 | Gemma 4 26B A4B Google DeepMind | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.07/$0.23 |
| #288 | Gemma 4 31B Google DeepMind | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.20/$0.40 |
| #332 | Qwen: Qwen3.5-9B Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.17/$0.25 |
| #331 | Qwen: Qwen3.5-35B-A3B Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.14/$1.00 |
| #333 | Qwen: Qwen3.5-Flash Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.07/$0.26 |
| #272 | ByteDance Seed: Seed-2.0-Mini ByteDance Research | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.10/$0.40 |
| #314 | Nemotron 3 Nano 30B A3B NVIDIA AI & NIMOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.06/$0.24 |
| #341 | Voxtral Small 24B 2507 Mistral AIOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.10/$0.30 |
| #296 | gpt-oss-safeguard-20b OpenAI | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.07/$0.30 |
| #330 | Qwen: Qwen3 VL 8B Instruct Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.25/$0.75 |
| #329 | Qwen: Qwen3 VL 30B A3B Thinking Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.29/$1.00 |
| #328 | Qwen: Qwen3 VL 30B A3B Instruct Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.15/$0.60 |
| #326 | Qwen: Qwen3 Coder Flash Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.20/$0.97 |
| #292 | GPT-5 Nano OpenAI | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.05/$0.40 |
| #295 | gpt-oss-120b OpenAI | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.15/$0.60 |
| #324 | Qwen: Qwen3 Coder 30B A3B Instruct Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.07/$0.28 |
| #322 | Qwen: Qwen3 30B A3B Instruct 2507 Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.10/$0.30 |
| #325 | Qwen: Qwen3 Coder 480B A35B Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.30/$1.00 |
| #320 | Qwen: Qwen3 235B A22B Instruct 2507 Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.09/$0.55 |
| #297 | Hunyuan A13B Instruct TencentOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.14/$0.57 |
| #271 | ByteDance Seed: Seed 1.6 Flash ByteDance Research | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.07/$0.30 |
| #321 | Qwen: Qwen3 30B A3B Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.12/$0.50 |
| #319 | Qwen: Qwen3 14B Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.12/$0.24 |
| #323 | Qwen: Qwen3 32B Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.08/$0.28 |
| #284 | Gemini 2.5 Flash Lite Google DeepMind | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.10/$0.40 |
| #308 | Llama 4 Maverick Meta AIOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.19/$0.65 |
| #309 | Llama 4 Scout Meta AIOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.10/$0.30 |
| #286 | Gemma 3 27B Google DeepMind | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.08/$0.35 |
| #339 | Saba Mistral AIOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.20/$0.60 |
| #327 | Qwen: Qwen3 Coder Next Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.12/$0.80 |
| #318 | Qwen: Qwen2.5 VL 72B Instruct Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.80/$1.00 |
| #317 | Qwen: Qwen-Plus Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.26/$0.78 |
| #278 | DeepSeek V3.2 DeepSeekOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.26/$0.38 |
| #279 | DeepSeek V3.2 Exp DeepSeekOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.27/$0.41 |
| #277 | DeepSeek V3.1 Terminus DeepSeekOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.27/$1.00 |
| #276 | DeepSeek V3.1 DeepSeekOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.25/$0.95 |
| #307 | Llama 3.3 70B Instruct Meta AIOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.10/$0.32 |
| #270 | Amazon: Nova Lite 1.0 Amazon AWS Bedrock | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.06/$0.24 |
| #316 | Perplexity: Sonar Perplexity AI | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $1.00/$1.00 |
| #338 | Qwen2.5 Coder 32B Instruct Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.66/$1.00 |
| #305 | Llama 3.2 1B Instruct Meta AIOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.03/$0.20 |
| #306 | Llama 3.2 3B Instruct Meta AIOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.05/$0.33 |
| #337 | Qwen2.5 72B Instruct Alibaba Cloud / QwenOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.36/$0.40 |
| #275 | Command R (08-2024) Cohere | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.15/$0.60 |
| #304 | Llama 3.1 70B Instruct Meta AIOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.40/$0.40 |
| #290 | GPT-4o-mini OpenAI | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.15/$0.60 |
| #291 | GPT-4o-mini OpenAI | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.15/$0.60 |
| #285 | Gemma 2 27B Google DeepMind | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.65/$0.65 |
| #274 | Codestral 2508 Mistral AIOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.30/$0.90 |
| #313 | Mistral Small 4 Mistral AIOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.15/$0.60 |
| #312 | Mistral Small 3.1 24B Mistral AIOpen | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.35/$0.56 |
| #346 | Z.ai: GLM 4.7 Flash Zhipu AI (Z.ai)Open | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.06/$0.40 |
| #345 | Z.ai: GLM 4.6V Zhipu AI (Z.ai)Open | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.30/$0.90 |
| #344 | Z.ai: GLM 4.5 Air Zhipu AI (Z.ai)Open | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.13/$0.85 |
| #289 | GPT-4.1 Nano OpenAI | 71.3% | 74.5% | 72.9% | 72.1% | 68.9% | 71.3% | 130 tok/s | $0.10/$0.40 |
| #347 | GPT-4.5 OpenAIFrontier | 71.0% | 85.0% | 70.5% | 80.0% | 81.5% | 91.5% | 42 tok/s | $75.00/$150.00 |
| #348 | BharatGPT-14B CoRover / BharatGPT | 70.8% | — | — | — | — | — | 110 tok/s | $0.12/$0.36 |
| #349 | Kimi k1.5 Moonshot AI | 70.5% | — | — | — | — | — | 48 tok/s | $1.00/$4.00 |
| #350 | Bulbul v3 (Text-to-Speech) Sarvam AI | 70.0% | — | — | — | — | — | 150 tok/s | $0.10/$0.30 |
| #351 | Claude 3.5 Sonnet Anthropic | 69.8% | 85.0% | 72.8% | 78.4% | 77.8% | 89.5% | 75 tok/s | $3.00/$15.00 |
| #352 | Amazon Nova Lite Amazon AWS Bedrock | 69.5% | — | — | — | — | — | 200 tok/s | $0.06/$0.24 |
| #353 | Amazon Nova Lite 1.0 Amazon AWS Bedrock | 69.5% | — | — | — | — | — | 160 tok/s | $0.06/$0.24 |
| #354 | Reka Core Reka AI | 69.2% | — | — | — | — | — | 55 tok/s | $3.00/$15.00 |
| #355 | Hanooman 7B Hanooman AI (SML)Open | 68.5% | — | — | — | — | — | 125 tok/s | $0.06/$0.18 |
| #356 | Phi-4-mini Microsoft Research & AzureOpen | 68.4% | — | — | — | — | — | 195 tok/s | $0.02/$0.05 |
| #358 | Solar Pro Upstage | 68.0% | — | — | — | — | — | 90 tok/s | $0.25/$0.25 |
| #357 | IndicTrans-2 AI4BharatOpen | 68.0% | — | — | — | — | — | 220 tok/s | $0.02/$0.04 |
| #363 | DeepSeek-V3 DeepSeekOpen | 67.8% | 81.9% | 69.2% | 78.9% | 74.2% | 87.5% | 62 tok/s | $0.14/$0.28 |
| #371 | Lyria 3 Pro Google DeepMindFrontier | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $3.00/$12.00 |
| #388 | TypeSafe: Jev Router TypeSafe AI | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.10/$0.20 |
| #389 | Upstage: Solar Mini 4 Upstage | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.05/$0.20 |
| #387 | Switchyard NVIDIA AI & NIMOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.20/$0.60 |
| #379 | Muse Spark 1.3 Contributor Meta AIOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.10/$0.20 |
| #390 | Z.ai: GLM 5.3 Flash Zhipu AI (Z.ai)Open | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.02/$0.15 |
| #381 | Nemotron 3.5 Lightning NVIDIA AI & NIMOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.07/$0.20 |
| #378 | Muse Spark 1.2 Contributor Meta AIOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.10/$0.20 |
| #384 | Qwen: Qwen3.7 Flash Alibaba Cloud / QwenOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.03/$0.13 |
| #380 | Nemotron 3.5 Content Safety NVIDIA AI & NIMOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.20/$0.20 |
| #367 | Hy-MT2-1.8B TencentOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.04/$0.18 |
| #362 | DeepSeek V4 Flash 0423 DeepSeekOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.09/$0.18 |
| #370 | Lyria 3 Clip Google DeepMind | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.50/$2.00 |
| #385 | Reka Edge Reka AI | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.10/$0.10 |
| #372 | Ministral 3 14B 2512 Mistral AIOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.20/$0.20 |
| #366 | gpt-oss-20b OpenAI | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.02/$0.09 |
| #360 | ByteDance: UI-TARS 7B ByteDance Research | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.10/$0.20 |
| #369 | Llama Guard 4 12B Meta AIOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.18/$0.18 |
| #365 | Gemma 3 4B Google DeepMind | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.05/$0.10 |
| #364 | Gemma 3 12B Google DeepMind | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.05/$0.15 |
| #386 | Reka Flash 3 Reka AI | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.10/$0.20 |
| #377 | Mistral Small 3.2 24B Mistral AIOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.07/$0.20 |
| #376 | Mistral Small 3 Mistral AIOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.05/$0.08 |
| #382 | Phi 4 Microsoft Research & Azure | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.07/$0.14 |
| #361 | Command R7B (12-2024) Cohere | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.04/$0.15 |
| #359 | Amazon: Nova Micro 1.0 Amazon AWS Bedrock | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.04/$0.14 |
| #374 | Ministral 3 8B 2512 Mistral AIOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.15/$0.15 |
| #373 | Ministral 3 3B 2512 Mistral AIOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.10/$0.10 |
| #383 | Qwen: Qwen2.5 7B Instruct Alibaba Cloud / QwenOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.10/$0.20 |
| #368 | Llama 3.1 8B Instruct Meta AIOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.05/$0.08 |
| #375 | Mistral Nemo Mistral AIOpen | 67.8% | 70.8% | 69.3% | 68.5% | 65.5% | 67.8% | 130 tok/s | $0.03/$0.03 |
| #391 | Gemini 2.0 Flash Google DeepMind | 67.5% | 82.0% | 68.4% | 79.1% | 75.0% | 88.7% | 185 tok/s | $0.10/$0.40 |
| #392 | DBRX Instruct DatabricksOpen | 67.2% | — | — | — | — | — | 70 tok/s | $0.60/$0.60 |
| #393 | Qwen 2.5 Coder 32B Alibaba Cloud / QwenOpen | 67.0% | — | 74.0% | — | — | — | 75 tok/s | $0.20/$0.60 |
| #395 | Llama 3.1 405B Meta AIOpen | 66.8% | 81.0% | 67.0% | 77.5% | 74.0% | 86.5% | 32 tok/s | $2.00/$2.00 |
| #396 | Sarvam 2B (Sarvam-1) Sarvam AIOpen | 66.8% | — | — | — | — | — | 165 tok/s | $0.05/$0.15 |
| #394 | Gemma 2 9B Google DeepMindOpen | 66.8% | 69.0% | 64.0% | 68.0% | 65.5% | 67.5% | 130 tok/s | $0.10/$0.20 |
| #397 | Snowflake Arctic SnowflakeOpen | 66.5% | — | — | — | — | — | 75 tok/s | $0.80/$0.80 |
| #398 | GPT-4o OpenAI | 66.4% | 81.5% | 66.5% | 76.8% | 78.4% | 90.8% | 70 tok/s | $2.50/$10.00 |
| #399 | Llama 3.3 70B Meta AIOpen | 65.2% | 79.5% | 65.1% | 76.2% | 73.0% | 86.2% | 72 tok/s | $0.40/$0.40 |
| #400 | Airavata 7B AI4BharatOpen | 65.0% | — | — | — | — | — | 140 tok/s | $0.05/$0.10 |
| #401 | Amazon Nova Micro 1.0 Amazon AWS Bedrock | 64.2% | — | — | — | — | — | 240 tok/s | $0.04/$0.14 |
| #402 | Gemini 1.5 Pro Google DeepMind | 64.1% | — | — | — | — | — | 55 tok/s | $1.25/$5.00 |
| #403 | Mistral Large 2 Mistral AI | 63.4% | — | — | — | — | — | 55 tok/s | $2.00/$6.00 |
| #404 | Gemma 2 2B Google DeepMindOpen | 56.4% | 58.0% | 52.0% | 54.5% | 55.0% | 60.0% | 180 tok/s | $0.05/$0.10 |
| #405 | GPT-4o mini OpenAI | 56.2% | — | — | — | — | — | 125 tok/s | $0.15/$0.60 |
| #594 | Hy4 TencentFrontier | — | — | — | — | — | — | 100 tok/s | $0.83/$2.50 |
| #582 | GPT-5.6 Luna OpenAIFrontier | — | — | — | — | — | — | 100 tok/s | $0.20/$1.20 |
| #480 | DeepSeek V4 Flash 0731 DeepSeek | — | — | — | — | — | — | 100 tok/s | $0.12/$0.24 |
| #625 | Nemotron 3 Ultra NVIDIA AI & NIM | — | — | — | — | — | — | 100 tok/s | $2.50/$7.50 |
| #618 | MiMo-V2.6-Flash Xiaomi | — | — | — | — | — | — | 100 tok/s | $0.14/$0.28 |
| #617 | MiMo-V2.5 Xiaomi | — | — | — | — | — | — | 100 tok/s | $0.40/$2.00 |
| #676 | Sonar Large Perplexity AI | — | — | — | — | — | — | 85 tok/s | $1.00/$1.00 |
| #468 | Codestral 25.01 Mistral AIOpen | — | — | — | — | — | — | 90 tok/s | $0.20/$0.60 |
| #431 | Claude 3 Opus Anthropic | — | — | — | — | — | — | 30 tok/s | $15.00/$75.00 |
| #435 | Claude 3.5 Haiku Anthropic | — | — | — | — | — | — | 95 tok/s | $0.80/$4.00 |
| #474 | Command R+ Cohere | — | — | — | — | — | — | 50 tok/s | $2.50/$10.00 |
| #497 | Gemini 1.5 Flash Google DeepMind | — | — | — | — | — | — | 140 tok/s | $0.07/$0.30 |
| #410 | Amazon Nova 2 Lite Amazon AWS Bedrock | — | — | — | — | — | — | 100 tok/s | $0.30/$2.50 |
| #651 | Qwen 3.8 Max Prime Alibaba Cloud / Qwen | — | — | — | — | — | — | 100 tok/s | $4.00/$12.00 |
| #653 | Qwen2.5-14B-Instruct-1M Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #657 | Qwen3-14B Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #661 | Qwen3-32B Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #654 | Qwen2.5-7B-Instruct-1M Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #598 | Jamba-1.5-mini AI21 Labs | — | — | — | — | — | — | — | $0.50/$2.00 |
| #493 | EXAONE-4.0-32B LG AI Research | — | — | — | — | — | — | — | $0.50/$2.00 |
| #566 | GPT-5 OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #589 | GPT-5.6 Terra OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #572 | GPT-5.4 mini OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #573 | GPT-5.4 nano OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #567 | GPT-5 OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #568 | GPT-5 + SWE-agent OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #571 | GPT-5-2 Codex OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #570 | GPT-5-2 OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #569 | GPT-5 Mini OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #472 | Codex + GPT-5.6 Terra (max; TB 2.1) OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #590 | GPT-5.6 Terra OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #601 | Kimi K2.6 OpenAI | — | — | — | — | — | — | — | $0.80/$2.40 |
| #452 | Claude Mythos Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #457 | Claude Opus 4.7 Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #623 | Muse Spark 1.1 Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #665 | Qwen3.7 Max Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #528 | GLM-5.1 Zhipu AI (Z.ai) | — | — | — | — | — | — | — | $0.14/$0.28 |
| #621 | MiniMax M3 MiniMax | — | — | — | — | — | — | — | $0.20/$1.10 |
| #455 | Claude Opus 4.6 Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #523 | Gemma 4 31B Google DeepMind | — | — | — | — | — | — | — | $0.25/$0.50 |
| #506 | Gemini 3.1 Flash-Lite Google DeepMind | — | — | — | — | — | — | — | $0.10/$0.40 |
| #522 | Gemma 4 26B-A4B Google DeepMind | — | — | — | — | — | — | — | $0.25/$0.50 |
| #521 | Gemma 4 12B Google DeepMind | — | — | — | — | — | — | — | $0.15/$0.30 |
| #507 | Gemini 3.1 Pro Google DeepMind | — | — | — | — | — | — | — | $2.50/$10.00 |
| #525 | Gemma 4 E4B Google DeepMind | — | — | — | — | — | — | — | $0.05/$0.10 |
| #501 | Gemini 3 Flash Google DeepMind | — | — | — | — | — | — | — | $0.15/$0.60 |
| #524 | Gemma 4 E2B Google DeepMind | — | — | — | — | — | — | — | $0.05/$0.10 |
| #511 | Gemini 3.6 Flash Google DeepMind | — | — | — | — | — | — | — | $0.15/$0.60 |
| #510 | Gemini 3.5 Flash-Lite Google DeepMind | — | — | — | — | — | — | — | $0.10/$0.40 |
| #512 | Gemini 3.6 Flash Google DeepMind | — | — | — | — | — | — | — | $0.15/$0.60 |
| #583 | GPT-5.6 Luna OpenAI | — | — | — | — | — | — | — | $5.00/$20.00 |
| #471 | Codex + GPT-5.6 Luna (max; TB 2.1) OpenAI | — | — | — | — | — | — | — | $5.00/$20.00 |
| #581 | GPT-5.5 Pro (High) OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #588 | GPT-5.6 Sol (xHigh) OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #579 | GPT-5.5 (xHigh) OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #587 | GPT-5.6 Sol (Max) OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #577 | GPT-5.5 (High) OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #574 | GPT-5.5 OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #578 | GPT-5.5 (xhigh, expected performance) OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #591 | GPT-5.6-Sol (max, expected performance) OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #585 | GPT-5.6 Sol OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #575 | GPT-5.5 OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #580 | GPT-5.5 high OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #470 | Codex + GPT-5.5 (xhigh; TB 2.1) OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #687 | Terminus 2 + GPT-5.5 (xhigh; TB 2.1) OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #584 | GPT-5.6 Luna OpenAI | — | — | — | — | — | — | — | $5.00/$20.00 |
| #586 | GPT-5.6 Sol OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #576 | GPT-5.5 OpenAI | — | — | — | — | — | — | — | $10.00/$40.00 |
| #449 | Claude Code + Opus 4.8 (high; TB 2.1) Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #450 | Claude Code + Sonnet 5 (high; TB 2.1) Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #619 | mini-SWE-agent + Muse Spark 1.1 (xhigh; TB 2.1) Meta AIOpen | — | — | — | — | — | — | — | $2.50/$10.00 |
| #680 | SWE-1.7 Cognition AI | — | — | — | — | — | — | — | $2.50/$10.00 |
| #462 | Claude Sonnet 5 Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #659 | Qwen3-235B-A22B-Thinking-2507 Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #658 | Qwen3-235B-A22B Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #476 | Cursor CLI + Grok 4.5 (high; TB 2.1) xAI | — | — | — | — | — | — | — | $3.00/$15.00 |
| #592 | Grok 4.5 xAI | — | — | — | — | — | — | — | $3.00/$15.00 |
| #529 | GLM-5.2 Zhipu AI (Z.ai) | — | — | — | — | — | — | — | $0.14/$0.28 |
| #602 | Kimi K2.7 Code Moonshot AI | — | — | — | — | — | — | — | $0.80/$2.40 |
| #451 | Claude Fable 5 Anthropic | — | — | — | — | — | — | — | $10.00/$50.00 |
| #446 | Claude Code + Fable 5 (xhigh; TB 2.1) Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #684 | Terminus 2 + Fable 5 (high; TB 2.1) Anthropic | — | — | — | — | — | — | — | $10.00/$50.00 |
| #460 | Claude Opus 4.8 (High) Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #458 | Claude Opus 4.8 Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #459 | Claude Opus 4.8 Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #667 | Qwen3.7 Plus (qwen3-7-plus; closed) Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #666 | Qwen3.7 Max (qwen3-7-max; closed) Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #509 | Gemini 3.5 Flash Google DeepMind | — | — | — | — | — | — | — | $0.15/$0.60 |
| #503 | Gemini 3 Pro Google DeepMind | — | — | — | — | — | — | — | $2.50/$10.00 |
| #504 | Gemini 3 Pro Google DeepMind | — | — | — | — | — | — | — | $2.50/$10.00 |
| #685 | Terminus 2 + Gemini 3 Pro (high; TB 2.1) Google DeepMind | — | — | — | — | — | — | — | $2.50/$10.00 |
| #513 | Gemini CLI + Gemini 3 Pro (high; TB 2.1) Google DeepMind | — | — | — | — | — | — | — | $2.50/$10.00 |
| #505 | Gemini 3 Pro Google DeepMind | — | — | — | — | — | — | — | $2.50/$10.00 |
| #514 | Gemini CLI + Gemini 3.1 Pro (high; TB 2.1) Google DeepMind | — | — | — | — | — | — | — | $2.50/$10.00 |
| #686 | Terminus 2 + Gemini 3.1 Pro (high; TB 2.1) Google DeepMind | — | — | — | — | — | — | — | $2.50/$10.00 |
| #448 | Claude Code + Opus 4.7 (max; TB 2.1) Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #688 | Terminus 2 + Opus 4.7 (max; TB 2.1) Anthropic | — | — | — | — | — | — | — | $0.50/$2.00 |
| #447 | Claude Code + GLM-5.1 (max; TB 2.1) Zhipu AI (Z.ai) | — | — | — | — | — | — | — | $3.00/$15.00 |
| #663 | Qwen3.6-27B Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #444 | Claude 4.7 (High) Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #445 | Claude 4.7 (Max) Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #664 | Qwen3.6-35B-A3B Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #679 | SWE-1.6 Cognition AI | — | — | — | — | — | — | — | $2.50/$10.00 |
| #508 | Gemini 3.1 Pro Google DeepMind | — | — | — | — | — | — | — | $2.50/$10.00 |
| #600 | Kimi K2.5 OpenAI | — | — | — | — | — | — | — | $0.80/$2.40 |
| #442 | Claude 4.5 Opus Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #456 | Claude Opus 4.6 Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #443 | Claude 4.5 Sonnet Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #441 | Claude 4.5 Haiku Anthropic | — | — | — | — | — | — | — | $0.80/$4.00 |
| #502 | Gemini 3 Flash Google DeepMind | — | — | — | — | — | — | — | $0.15/$0.60 |
| #527 | GLM-5 Zhipu AI (Z.ai) | — | — | — | — | — | — | — | $0.14/$0.28 |
| #620 | MiniMax M2.5 MiniMax | — | — | — | — | — | — | — | $0.20/$1.10 |
| #463 | Claude-4-Sonnet Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #662 | Qwen3-Next-80B-A3B-Thinking Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #660 | Qwen3-30B-A3B-Thinking-2507 Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #622 | MiniMax-M2 MiniMax | — | — | — | — | — | — | — | $0.20/$1.10 |
| #411 | Anthropic Opus 4.6 (Max) Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #626 | NVARC OpenAI | — | — | — | — | — | — | — | $2.00/$6.00 |
| #461 | Claude Sonnet 4 + SWE-agent Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #454 | Claude Opus 4.1 + SWE-agent Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #656 | Qwen3 32B + SWE-agent Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $2.50/$10.00 |
| #453 | Claude Opus 4 Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #440 | Claude 4 Sonnet Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #518 | Gemini-2.5-Flash Google DeepMind | — | — | — | — | — | — | — | $0.15/$0.60 |
| #638 | o4-mini OpenAI | — | — | — | — | — | — | — | $1.25/$5.00 |
| #520 | Gemma 3 27B Google DeepMind | — | — | — | — | — | — | — | $0.25/$0.50 |
| #635 | o3 OpenAI | — | — | — | — | — | — | — | $20.00/$80.00 |
| #636 | o3-low OpenAI | — | — | — | — | — | — | — | $20.00/$80.00 |
| #519 | Gemini-2.5-Pro Google DeepMind | — | — | — | — | — | — | — | $2.00/$8.00 |
| #500 | Gemini 2.5 Pro 06-05 Google DeepMind | — | — | — | — | — | — | — | $2.00/$8.00 |
| #412 | ARChitects (Kaggle 2024 winner) OpenAI | — | — | — | — | — | — | — | $5.00/$15.00 |
| #484 | DeepSeek-R1 DeepSeekOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #555 | GPT-4.5 OpenAI | — | — | — | — | — | — | — | $75.00/$150.00 |
| #539 | GPT-4 OpenAI | — | — | — | — | — | — | — | $75.00/$150.00 |
| #540 | GPT-4 OpenAI | — | — | — | — | — | — | — | $75.00/$150.00 |
| #530 | Goedel-Prover OpenAI | — | — | — | — | — | — | — | $5.00/$15.00 |
| #641 | OpenAI o3-mini (High) OpenAI | — | — | — | — | — | — | — | $2.20/$8.80 |
| #637 | o3-mini OpenAI | — | — | — | — | — | — | — | $1.10/$4.40 |
| #486 | DeepSeek-R1-0528 DeepSeekOpen | — | — | — | — | — | — | — | $0.55/$2.19 |
| #485 | DeepSeek-R1 DeepSeekOpen | — | — | — | — | — | — | — | $0.55/$2.19 |
| #488 | DeepSeek-V3 DeepSeekOpen | — | — | — | — | — | — | — | $0.14/$0.28 |
| #489 | DeepSeek-V3 DeepSeekOpen | — | — | — | — | — | — | — | $0.14/$0.28 |
| #478 | DeepSeek V3 DeepSeekOpen | — | — | — | — | — | — | — | $0.14/$0.28 |
| #490 | DeepSeek-V3 DeepSeekOpen | — | — | — | — | — | — | — | $0.14/$0.28 |
| #479 | DeepSeek V3.2 DeepSeekOpen | — | — | — | — | — | — | — | $0.14/$0.28 |
| #599 | Jeremy Berman system OpenAI | — | — | — | — | — | — | — | $2.50/$10.00 |
| #627 | o1 OpenAI | — | — | — | — | — | — | — | $15.00/$60.00 |
| #628 | o1 OpenAI | — | — | — | — | — | — | — | $15.00/$60.00 |
| #631 | o1 (198-task Diamond offline) OpenAI | — | — | — | — | — | — | — | $15.00/$60.00 |
| #649 | Qwen 2.5 Coder 32B Instruct Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #650 | Qwen 2.5 Coder 32B Instruct Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #655 | Qwen2.5-Coder 32B Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #421 | best frontier model OpenAI | — | — | — | — | — | — | — | $5.00/$15.00 |
| #593 | Grok Beta xAI | — | — | — | — | — | — | — | $5.00/$15.00 |
| #436 | Claude 3.5 Sonnet Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #437 | Claude 3.5 Sonnet Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #438 | Claude 3.5 Sonnet Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #439 | Claude 3.5 Sonnet Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #652 | Qwen2.5 72B Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #633 | o1-mini OpenAI | — | — | — | — | — | — | — | $1.10/$4.40 |
| #629 | o1 OpenAI | — | — | — | — | — | — | — | $15.00/$60.00 |
| #630 | o1 OpenAI | — | — | — | — | — | — | — | $15.00/$60.00 |
| #634 | o1-mini OpenAI | — | — | — | — | — | — | — | $1.10/$4.40 |
| #639 | OpenAI o1 OpenAI | — | — | — | — | — | — | — | $15.00/$60.00 |
| #632 | O1 Mini OpenAI | — | — | — | — | — | — | — | $1.10/$4.40 |
| #640 | OpenAI o1-mini OpenAI | — | — | — | — | — | — | — | $1.10/$4.40 |
| #487 | DeepSeek-V2.5 DeepSeekOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #597 | Jamba-1.5-large AI21 Labs | — | — | — | — | — | — | — | $0.50/$2.00 |
| #613 | Llama 3.1 405B Meta AIOpen | — | — | — | — | — | — | — | $2.00/$6.00 |
| #564 | GPT-4o Mini OpenAI | — | — | — | — | — | — | — | $0.15/$0.60 |
| #482 | DeepSeek-Coder-V2-Instruct DeepSeekOpen | — | — | — | — | — | — | — | $0.14/$0.28 |
| #483 | DeepSeek-Coder-V2-Instruct DeepSeekOpen | — | — | — | — | — | — | — | $0.14/$0.28 |
| #561 | GPT-4o (few-shot) OpenAI | — | — | — | — | — | — | — | $2.50/$10.00 |
| #556 | GPT-4o OpenAI | — | — | — | — | — | — | — | $2.50/$10.00 |
| #557 | GPT-4o OpenAI | — | — | — | — | — | — | — | $2.50/$10.00 |
| #562 | GPT-4o (full benchmark) OpenAI | — | — | — | — | — | — | — | $2.50/$10.00 |
| #558 | GPT-4o OpenAI | — | — | — | — | — | — | — | $2.50/$10.00 |
| #563 | GPT-4o + SWE-agent OpenAI | — | — | — | — | — | — | — | $2.50/$10.00 |
| #559 | GPT-4o OpenAI | — | — | — | — | — | — | — | $2.50/$10.00 |
| #560 | GPT-4o (198-task Diamond offline) OpenAI | — | — | — | — | — | — | — | $2.50/$10.00 |
| #608 | Llama 3 70B Meta AIOpen | — | — | — | — | — | — | — | $0.60/$1.20 |
| #611 | llama 3 70b-instruct Meta AIOpen | — | — | — | — | — | — | — | $0.60/$1.20 |
| #693 | UN codellama-34b-instruct Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #612 | llama 3 8b-instruct Meta AIOpen | — | — | — | — | — | — | — | $0.10/$0.20 |
| #609 | Llama 3 70B Meta AIOpen | — | — | — | — | — | — | — | $0.60/$1.20 |
| #465 | CodeLlama-34B base (Mercury-eval Overall Beyond, 5 samples) Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #610 | Llama 3 70B Meta AIOpen | — | — | — | — | — | — | — | $0.60/$1.20 |
| #467 | CodeQwen1.5-7B-Chat Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #466 | CodeQwen1.5-7B base (Mercury-eval Overall Beyond, 5 samples) Alibaba Cloud / QwenOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #550 | GPT-4 Turbo + SWE-agent OpenAI | — | — | — | — | — | — | — | $10.00/$30.00 |
| #553 | GPT-4-Turbo (April 2024) OpenAI | — | — | — | — | — | — | — | $10.00/$30.00 |
| #551 | GPT-4-Turbo OpenAI | — | — | — | — | — | — | — | $10.00/$30.00 |
| #552 | GPT-4-Turbo OpenAI | — | — | — | — | — | — | — | $10.00/$30.00 |
| #432 | Claude 3 Opus Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #434 | Claude 3 Opus (BM25 retrieval) Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #433 | Claude 3 Opus Anthropic | — | — | — | — | — | — | — | $15.00/$75.00 |
| #678 | StarCoder2-15B base (Mercury-eval Overall Beyond, 5 samples) OpenAI | — | — | — | — | — | — | — | $0.15/$0.45 |
| #603 | Kimi-Chat (paper Table 3 Average) OpenAI | — | — | — | — | — | — | — | $0.80/$2.40 |
| #699 | YaRN-Mistral (paper Table 3 Average) Mistral AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #498 | Gemini 1.5 Pro Google DeepMind | — | — | — | — | — | — | — | $1.25/$5.00 |
| #499 | Gemini 1.5 Pro 002 Google DeepMind | — | — | — | — | — | — | — | $1.25/$5.00 |
| #517 | Gemini-1.5-pro Google DeepMind | — | — | — | — | — | — | — | $1.25/$5.00 |
| #694 | UN codellama-70b-instruct Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #526 | GLM-4.7 (glm-4-7; open weight) Zhipu AI (Z.ai) | — | — | — | — | — | — | — | $0.14/$0.28 |
| #516 | Gemini Ultra 1.0 Google DeepMind | — | — | — | — | — | — | — | $1.25/$5.00 |
| #515 | Gemini Ultra Google DeepMind | — | — | — | — | — | — | — | $1.25/$5.00 |
| #646 | PaLM 540B (translate-to-English CoT) Google DeepMind | — | — | — | — | — | — | — | $20.00/$20.00 |
| #481 | DeepSeek-Coder-33B base (Mercury-eval Overall Beyond, 5 samples) DeepSeekOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #549 | GPT-4 Turbo (1106) OpenAI | — | — | — | — | — | — | — | $30.00/$60.00 |
| #616 | LongChat-v1.5-7B-32k (paper Table 3 OverAll) OpenAI | — | — | — | — | — | — | — | $0.08/$0.24 |
| #697 | XGen-7B-8k (paper Table 3 OverAll) OpenAI | — | — | — | — | — | — | — | $0.08/$0.24 |
| #596 | InternLM-7B-8k (paper Table 3 OverAll) OpenAI | — | — | — | — | — | — | — | $0.08/$0.24 |
| #696 | Vicuna-v1.5-7B-16k (paper Table 3 OverAll) OpenAI | — | — | — | — | — | — | — | $0.08/$0.24 |
| #615 | Llama2-7B-chat-4k (paper Table 3 OverAll) Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #423 | ChatGLM2-6B (paper Table 3 OverAll) Zhipu AI (Z.ai) | — | — | — | — | — | — | — | $0.06/$0.18 |
| #424 | ChatGLM2-6B-32k (paper Table 3 OverAll) Zhipu AI (Z.ai) | — | — | — | — | — | — | — | $0.06/$0.18 |
| #692 | UN codellama-13b-instruct Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #607 | Llama 2 70B Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #430 | Claude 2 (paper Table 3 Average) Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #429 | Claude 2 (BM25 retrieval) Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #681 | T0pp (paper Table 3 Avg) OpenAI | — | — | — | — | — | — | — | $0.05/$0.10 |
| #477 | DaVinci003 (paper Table 3 Avg) OpenAI | — | — | — | — | — | — | — | $20.00/$20.00 |
| #426 | ChatGPT (paper Table 3 Avg) OpenAI | — | — | — | — | — | — | — | $0.50/$1.50 |
| #428 | Claude (paper Table 3 Avg) Anthropic | — | — | — | — | — | — | — | $3.00/$15.00 |
| #495 | Flan-T5 (paper Table 3 Avg) Google DeepMind | — | — | — | — | — | — | — | $0.05/$0.10 |
| #496 | Flan-UL2 (paper Table 3 Avg) Google DeepMind | — | — | — | — | — | — | — | $0.05/$0.10 |
| #475 | CPACE OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #689 | text-davinci-003 OpenAI | — | — | — | — | — | — | — | $20.00/$20.00 |
| #554 | GPT-4.1 OpenAI | — | — | — | — | — | — | — | $30.00/$60.00 |
| #546 | GPT-4 (paper Table 3 Average) OpenAI | — | — | — | — | — | — | — | $30.00/$60.00 |
| #565 | GPT-4V (full benchmark) OpenAI | — | — | — | — | — | — | — | $30.00/$60.00 |
| #547 | GPT-4 (paper Table 3 Avg) OpenAI | — | — | — | — | — | — | — | $30.00/$60.00 |
| #541 | GPT-4 OpenAI | — | — | — | — | — | — | — | $30.00/$60.00 |
| #545 | GPT-4 (May 2023) OpenAI | — | — | — | — | — | — | — | $30.00/$60.00 |
| #422 | Chameleon (GPT-4, Text-GT, tools) OpenAI | — | — | — | — | — | — | — | $30.00/$60.00 |
| #542 | GPT-4 OpenAI | — | — | — | — | — | — | — | $30.00/$60.00 |
| #543 | GPT-4 OpenAI | — | — | — | — | — | — | — | $30.00/$60.00 |
| #548 | GPT-4 base OpenAI | — | — | — | — | — | — | — | $30.00/$60.00 |
| #544 | GPT-4 (full MATH) OpenAI | — | — | — | — | — | — | — | $30.00/$60.00 |
| #538 | GPT-3.5-Turbo-16k (paper Table 3 OverAll) OpenAI | — | — | — | — | — | — | — | $0.50/$1.50 |
| #425 | ChatGPT (gpt-3.5-turbo) OpenAI | — | — | — | — | — | — | — | $0.50/$1.50 |
| #537 | gpt-3.5-turbo OpenAI | — | — | — | — | — | — | — | $0.50/$1.50 |
| #614 | LLaMA-65B Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #674 | SantaCoder-1.1B (MultiPL-HumanEval Python, pass@1) OpenAI | — | — | — | — | — | — | — | $0.04/$0.12 |
| #469 | Codex (code-davinci-002) OpenAI | — | — | — | — | — | — | — | $20.00/$20.00 |
| #642 | PaLM 540B Google DeepMind | — | — | — | — | — | — | — | $20.00/$20.00 |
| #695 | Vega v2 OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #532 | GPT-3 + PromptPG OpenAI | — | — | — | — | — | — | — | $20.00/$20.00 |
| #464 | code-davinci-002 (MultiPL-HumanEval Python, pass@1) OpenAI | — | — | — | — | — | — | — | $20.00/$20.00 |
| #595 | InCoder-6.7B (MultiPL-HumanEval Python, pass@1) Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #643 | PaLM 540B Google DeepMind | — | — | — | — | — | — | — | $20.00/$20.00 |
| #427 | Chinchilla 70B Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |
| #644 | PaLM 540B Google DeepMind | — | — | — | — | — | — | — | $20.00/$20.00 |
| #677 | ST-MoE-32B Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |
| #409 | AlphaCode 9B (test set, 10@100k, no clustering) Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |
| #407 | AlphaCode 41B (test set, 10@100k, no clustering) Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |
| #408 | AlphaCode 41B + clustering (test set, 10@100k) Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |
| #645 | PaLM 540B Google DeepMind | — | — | — | — | — | — | — | $20.00/$20.00 |
| #624 | Naive (paper Table 2 Avg) OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #604 | LED 1024 (paper Table 2 Avg) OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #606 | LED 4096 (paper Table 2 Avg) OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #605 | LED 16384 (paper Table 2 Avg) OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #416 | BART 256 (paper Table 2 Avg) Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #417 | BART 512 (paper Table 2 Avg) Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #415 | BART 1024 (paper Table 2 Avg) Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #531 | Gopher 280B Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |
| #535 | GPT-3 175B (fine-tuned) OpenAI | — | — | — | — | — | — | — | $20.00/$20.00 |
| #492 | ERNIE 3.0 Baidu | — | — | — | — | — | — | — | $0.50/$2.00 |
| #473 | Codex-12B (original paper, 164-task HumanEval pass@1 estimator) OpenAI | — | — | — | — | — | — | — | $20.00/$20.00 |
| #668 | Random (paper Table 3 R-1) OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #494 | Ext. Oracle (paper Table 3 R-1) OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #690 | TextRank (paper Table 3 R-1) OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #648 | PGNet (paper Table 3 R-1) OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #647 | PGNet (gold spans) (paper Table 3 R-1) OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #414 | BART (paper Table 3 R-1) Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #413 | BART (gold spans) (paper Table 3 R-1) Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #536 | GPT-3 175B (full MATH) OpenAI | — | — | — | — | — | — | — | $20.00/$20.00 |
| #675 | Seq2Seq (CodeSearchNet summarization, six-language overall BLEU) OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #691 | Transformer (CodeSearchNet summarization, six-language overall BLEU) OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #670 | RoBERTa encoder (CodeSearchNet summarization, six-language overall BLEU) Meta AIOpen | — | — | — | — | — | — | — | $0.20/$0.60 |
| #533 | GPT-3 175B OpenAI | — | — | — | — | — | — | — | $20.00/$20.00 |
| #534 | GPT-3 175B (few-shot) OpenAI | — | — | — | — | — | — | — | $20.00/$20.00 |
| #491 | ELECTRA-Large Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |
| #682 | T5 (ensemble) Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |
| #683 | T5-11B Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |
| #406 | ALBERT (ensemble) Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |
| #672 | RoBERTa-large OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #671 | RoBERTa ensemble OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #669 | RoBERTa OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #673 | RoBERTa-large (fine-tuned) OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #419 | BERT-Large (fine-tuned) Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |
| #698 | XLNet (ensemble) Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |
| #420 | BERT++ OpenAI | — | — | — | — | — | — | — | $0.50/$2.00 |
| #418 | BERT-Large Google DeepMind | — | — | — | — | — | — | — | $0.50/$2.00 |