AA-LCR (Long Context Reasoning)
Artificial Analysis long-context reasoning benchmark: questions that require reasoning across multiple long documents.
Actively evaluated by Artificial Analysis on current frontier models; no saturation evidence recorded.
Performance Timeline
Longitudinal progression of model scores against human baselines.Performance & Historical Trajectory
Empirical score progression across model release dates and evaluation rounds.
| Model | Score | Date | Source Type | Provenance |
|---|---|---|---|---|
| JT-35B-Flash | 65.7% | 2026-11-15 | independent | Source ↗ |
| Qwen3.5 Omni Plus | 63.7% | 2026-11-15 | independent | Source ↗ |
| Nova 2.0 Omni | 59.7% | 2026-11-15 | independent | Source ↗ |
| Qwen3.5-122B-A10B | 61.3% | 2026-11-15 | independent | Source ↗ |
| Gemma 4 12B | 35% | 2026-11-15 | independent | Source ↗ |
| Claude Sonnet 5.5 | 82.7% | 2026-11-15 | independent | Source ↗ |
| Gemma 3 270M | 0% | 2026-11-15 | independent | Source ↗ |
| Apodex 1.1 | 79.3% | 2026-11-15 | independent | Source ↗ |
| GPT-6.1 Sol | 83% | 2026-11-15 | independent | Source ↗ |
| Gemini 3.5 Flash-Lite | 76% | 2026-11-15 | independent | Source ↗ |
| Step 5 | 88.3% | 2026-11-15 | independent | Source ↗ |
| Qwen3.5 2B | 14% | 2026-11-15 | independent | Source ↗ |
| Qwen3 Omni 30B A3B Instruct | 0% | 2026-11-15 | independent | Source ↗ |
| Granite 4.2 3B | 24.3% | 2026-11-15 | independent | Source ↗ |
| Claude Fable 5.2 | 83.3% | 2026-11-15 | independent | Source ↗ |
| GPT-6.1 Terra | 82.7% | 2026-11-15 | independent | Source ↗ |
| Gemini 4 Carbon | 79.3% | 2026-11-15 | independent | Source ↗ |
| Nova 2.0 Pro | 64% | 2026-11-15 | independent | Source ↗ |
| Inkling | 77.3% | 2026-11-15 | independent | Source ↗ |
| Qwen3.5 397B A17B | 77.3% | 2026-11-15 | independent | Source ↗ |
| Granite 4.2 30B | 49% | 2026-11-15 | independent | Source ↗ |
| K2 Horizon 7B | 69.7% | 2026-11-15 | independent | Source ↗ |
| MiMo-V2.6-Flash | 74.3% | 2026-11-15 | independent | Source ↗ |
| Mistral Small 4 | 49.7% | 2026-11-15 | independent | Source ↗ |
| Solar Pro 4 | 70.7% | 2026-11-15 | independent | Source ↗ |
| gpt-oss-20b | 31% | 2026-11-15 | independent | Source ↗ |
| o3 | 74.7% | 2026-11-15 | independent | Source ↗ |
| K-EXAONE 2.0 | 60% | 2026-11-15 | independent | Source ↗ |
| GLM 5.3 Flash | 80% | 2026-11-15 | independent | Source ↗ |
| GPT-6 Luna | 83.3% | 2026-11-15 | independent | Source ↗ |
| North Mini Code | 37.3% | 2026-11-15 | independent | Source ↗ |
| GPT-6 Astra | 80.7% | 2026-11-15 | independent | Source ↗ |
| Granite 4.0 Micro | 7% | 2026-11-15 | independent | Source ↗ |
| Claude Haiku 5.5 | 82.7% | 2026-11-15 | independent | Source ↗ |
| Grok 4.7 | 76.7% | 2026-11-15 | independent | Source ↗ |
| Qwen3.5-9B | 46% | 2026-11-15 | independent | Source ↗ |
| Hermes 4 - Llama-3.1 70B | 4.7% | 2026-11-15 | independent | Source ↗ |
| Nemotron 3 Nano 30B A3B | 10.7% | 2026-11-15 | independent | Source ↗ |
| MiMo-V2.6-Pro | 86.3% | 2026-11-15 | independent | Source ↗ |
| Qwen3 Next 80B A3B Instruct | 52.7% | 2026-11-15 | independent | Source ↗ |
| MiniMax M3 | 83% | 2026-11-15 | independent | Source ↗ |
| Nemotron 3.5 Lightning | 60.3% | 2026-11-15 | independent | Source ↗ |
| NVIDIA Nemotron Nano 9B V2 | 24% | 2026-11-15 | independent | Source ↗ |
| Command A+ | 52.7% | 2026-11-15 | independent | Source ↗ |
| Claude Opus 5.5 | 84.7% | 2026-11-15 | independent | Source ↗ |
| G9v3-3B | 41.3% | 2026-11-15 | independent | Source ↗ |
| Qwen3.5 4B | 34.7% | 2026-11-15 | independent | Source ↗ |
| K2 Horizon 3.7B | 62.3% | 2026-11-15 | independent | Source ↗ |
| Olmo 3 7B Think | 0% | 2026-11-15 | independent | Source ↗ |
| HyperCLOVA X SEED Think (32B) | 13.7% | 2026-11-15 | independent | Source ↗ |
| HyperNova 60B 2605 | 36.3% | 2026-11-15 | independent | Source ↗ |
| Nova Micro | 13% | 2026-11-15 | independent | Source ↗ |
| Qwen3.8 27B | 82% | 2026-11-15 | independent | Source ↗ |
| Muse Spark Open | 78.3% | 2026-11-15 | independent | Source ↗ |
| INTELLECT-3 | 39.7% | 2026-11-15 | independent | Source ↗ |
| Muse Wonder | 80.7% | 2026-11-15 | independent | Source ↗ |
| Olmo 3.1 32B Think | 0% | 2026-11-15 | independent | Source ↗ |
| Nex-N2-Pro | 81.7% | 2026-11-15 | independent | Source ↗ |
| LFM2.5-VL-1.6B | 0% | 2026-11-15 | independent | Source ↗ |
| JT-MINI | 13% | 2026-11-15 | independent | Source ↗ |
| Molmo2-8B | 0% | 2026-11-15 | independent | Source ↗ |
| Qwen3.5 0.8B | 8% | 2026-11-15 | independent | Source ↗ |
| Ling-3.0-flash-VL | 78.3% | 2026-11-15 | independent | Source ↗ |
| MiniCPM-V 4.6 1.3B | 7% | 2026-11-15 | independent | Source ↗ |
| Sarvam 105B | 0% | 2026-11-15 | independent | Source ↗ |
| Llama 3.1 Instruct 405B | 25.3% | 2026-11-15 | independent | Source ↗ |
| Ring-flash-2.0 | 21% | 2026-11-15 | independent | Source ↗ |
| LFM2.5-1.2B-Instruct | 0% | 2026-11-15 | independent | Source ↗ |
| Gemini 4 Argon | 79.7% | 2026-11-15 | independent | Source ↗ |
| Apertus 70B Instruct | 0% | 2026-11-15 | independent | Source ↗ |
| Doubao Seed Code | 71.7% | 2026-11-15 | independent | Source ↗ |
| Gemma 4 E4B | 24% | 2026-11-15 | independent | Source ↗ |
| Ling 3.1 Flash 1019 | 82.3% | 2026-11-15 | independent | Source ↗ |
| K2 Horizon MoVA 36B A4B | 71.7% | 2026-11-15 | independent | Source ↗ |
| Granite 4.0 350M | 0% | 2026-11-15 | independent | Source ↗ |
| DeepSeek V4.1 Flash 1017 | 82.7% | 2026-11-15 | independent | Source ↗ |
| Muse Glimmer | 83.3% | 2026-11-15 | independent | Source ↗ |
| Kimi Linear 48B A3B Instruct | 28% | 2026-11-15 | independent | Source ↗ |
| Solar Open 100B | 41% | 2026-11-15 | independent | Source ↗ |
| GPT-5.3-Codex | 83.3% | 2026-11-15 | independent | Source ↗ |
| LFM2.5-1.2B-Thinking | 0% | 2026-11-15 | independent | Source ↗ |
| K2 Think V2 | 57% | 2026-11-15 | independent | Source ↗ |
| Nemotron 3 Ultra | 79.3% | 2026-11-15 | independent | Source ↗ |
| LongCat 2.0 | 65% | 2026-11-15 | independent | Source ↗ |
| Tri-21B-Think | 15.7% | 2026-11-15 | independent | Source ↗ |
| Granite 4.0 H Small | 11.3% | 2026-11-15 | independent | Source ↗ |
| Llama 3.2 Instruct 11B (Vision) | 12.7% | 2026-11-15 | independent | Source ↗ |
| LongCat Flash Lite | 28.3% | 2026-11-15 | independent | Source ↗ |
| Nova 2.0 Lite | 60.3% | 2026-11-15 | independent | Source ↗ |
| Solar Mini 4 | 83.3% | 2026-11-15 | independent | Source ↗ |
| MiniCPM5-2B | 59.3% | 2026-11-15 | independent | Source ↗ |
| Kimi K3.1 Pro | 86.3% | 2026-11-15 | independent | Source ↗ |
| Motif-2-12.7B-Reasoning | 14.7% | 2026-11-15 | independent | Source ↗ |
| Qwen3.6 35B A3B | 64.3% | 2026-11-15 | independent | Source ↗ |
| Ministral 3 3B | 17% | 2026-11-15 | independent | Source ↗ |
| Beam 1.0 | 78% | 2026-11-15 | independent | Source ↗ |
| Ling-3.0-flash-Fin | 73.7% | 2026-11-15 | independent | Source ↗ |
| Gemma 4 26B A4B | 65.7% | 2026-11-15 | independent | Source ↗ |
| NVIDIA Nemotron Nano 12B v2 VL | 41% | 2026-11-15 | independent | Source ↗ |
| Qwen3.5 Omni Flash | 52% | 2026-11-15 | independent | Source ↗ |
| Magistral Small 1.2 | 19.3% | 2026-11-15 | independent | Source ↗ |
| Ministral 3 14B | 26.3% | 2026-11-15 | independent | Source ↗ |
| Inkling Small | 75.7% | 2026-11-15 | independent | Source ↗ |
| Gemini 3.8 Flash | 81.3% | 2026-11-15 | independent | Source ↗ |
| Gemma 4 E2B | 16.3% | 2026-11-15 | independent | Source ↗ |
| Sarvam 30B | 0% | 2026-11-15 | independent | Source ↗ |
| Mercury 2.5 | 71.7% | 2026-11-15 | independent | Source ↗ |
| DeepSeek V4 Flash Vision | 81.3% | 2026-11-15 | independent | Source ↗ |
| MiniCPM5-1B | 6% | 2026-11-15 | independent | Source ↗ |
| Jamba 1.7 Large | 19.3% | 2026-11-15 | independent | Source ↗ |
| Nemotron 3.5 Bolt 74B-A9B | 69.7% | 2026-11-15 | independent | Source ↗ |
| Nanbeige4.1-3B | 0% | 2026-11-15 | independent | Source ↗ |
| Solar Open2 250B | 71.7% | 2026-11-15 | independent | Source ↗ |
| Ling 3.0 Tiny | 60.3% | 2026-11-15 | independent | Source ↗ |
| Celeris-1 | 38% | 2026-11-15 | independent | Source ↗ |
| Tiny Aya Global | 0% | 2026-11-15 | independent | Source ↗ |
| A.X-K2 | 70% | 2026-11-15 | independent | Source ↗ |
| Exaone 4.0 1.2B | 0% | 2026-11-15 | independent | Source ↗ |
| Hermes 4 - Llama-3.1 405B | 22.3% | 2026-11-15 | independent | Source ↗ |
| DeepSeek V4-Pro | 80.3% | 2026-11-15 | independent | Source ↗ |
| Magistral Medium 1.2 | 53% | 2026-11-15 | independent | Source ↗ |
| Apertus 8B Instruct | 0% | 2026-11-15 | independent | Source ↗ |
| Nemotron 3 Nano Omni 30B A3B Reasoning | 39.7% | 2026-11-15 | independent | Source ↗ |
| Kimi K2.7 Code | 79.3% | 2026-11-15 | independent | Source ↗ |
| Qwen3.8 2.4T A95B | 80.3% | 2026-11-15 | independent | Source ↗ |
| Olmo 3 7B Instruct | 0% | 2026-11-15 | independent | Source ↗ |
| Llama 4 Maverick | 50% | 2026-11-15 | independent | Source ↗ |
| Olmo 3.1 32B Instruct | 0% | 2026-11-15 | independent | Source ↗ |
| Ministral 3 8B | 25.7% | 2026-11-15 | independent | Source ↗ |
| Llama 3.3 Instruct 70B | 15.7% | 2026-11-15 | independent | Source ↗ |
| Nemotron Cascade 2 30B A3B | 39.3% | 2026-11-15 | independent | Source ↗ |
| Qwen3.8-Flash-Next | 79.7% | 2026-11-15 | independent | Source ↗ |
| K2 Horizon 0.9B | 6.3% | 2026-11-15 | independent | Source ↗ |
| NVIDIA Nemotron 3 Nano 4B | 21.7% | 2026-11-15 | independent | Source ↗ |
| Phi-4-mini | 15.3% | 2026-11-15 | independent | Source ↗ |
| K2-V2 | 35% | 2026-11-15 | independent | Source ↗ |
| Ling 3.1 Flash | 83% | 2026-11-15 | independent | Source ↗ |
| Granite 4.0 H 350M | 0% | 2026-11-15 | independent | Source ↗ |
| Qwen3.7 Plus | 73% | 2026-11-15 | independent | Source ↗ |
| Step3 VL 10B | 0% | 2026-11-15 | independent | Source ↗ |
| Llama 4 Scout | 27.7% | 2026-11-15 | independent | Source ↗ |
| Granite 4.2 8B | 45% | 2026-11-15 | independent | Source ↗ |
| Molmo 7B-D | 0% | 2026-11-15 | independent | Source ↗ |
| Motif 3 | 76% | 2026-11-15 | independent | Source ↗ |
| Qwen3.8 Max (0902) | 80.3% | 2026-11-15 | independent | Source ↗ |
| Hy3 | 79% | 2026-11-15 | independent | Source ↗ |
| Jamba 1.7 Mini | 16% | 2026-11-15 | independent | Source ↗ |
| Trinity Large Thinking | 38% | 2026-11-15 | independent | Source ↗ |
| Qwen3 Omni 30B A3B (Reasoning) | 0% | 2026-11-15 | independent | Source ↗ |
| K2 Horizon 375B A23B | 80% | 2026-11-15 | independent | Source ↗ |
| Gemini 3.1 Pro | 82% | 2026-11-15 | independent | Source ↗ |
| G9v3-39A5B | 65.3% | 2026-11-15 | independent | Source ↗ |
| DiffusionGemma 26B A4B | 19.7% | 2026-11-15 | independent | Source ↗ |
| GPT-5.5 Instant | 70% | 2026-11-15 | independent | Source ↗ |
| Falcon-H1R-7B | 11% | 2026-11-15 | independent | Source ↗ |
| Qwen3 Next 80B A3B (Reasoning) | 63.7% | 2026-11-15 | independent | Source ↗ |
| gpt-oss-120b | 52% | 2026-11-15 | independent | Source ↗ |
| GLM 5.3 | 79.7% | 2026-11-15 | independent | Source ↗ |
| Gemma 4 31B | 69.7% | 2026-11-15 | independent | Source ↗ |
| MiniMax M3.1 Flash | 79.7% | 2026-11-15 | independent | Source ↗ |
| Agnes 2.5 Pro Theta | 84.7% | 2026-11-15 | independent | Source ↗ |
| Granite 4.0 H 1B | 7% | 2026-11-15 | independent | Source ↗ |
| Reka Flash 3 | 0% | 2026-11-15 | independent | Source ↗ |
| Mistral Medium 3.5 | 69.3% | 2026-11-15 | independent | Source ↗ |
| Mi:dm K 2.5 Pro | 9% | 2026-11-15 | independent | Source ↗ |
| LFM2.5-2.6B | 5.7% | 2026-11-15 | independent | Source ↗ |
| LFM2.5-8B-A1B | 0% | 2026-11-15 | independent | Source ↗ |
| Nemotron 3.5 Super VL | 69% | 2026-11-15 | independent | Source ↗ |
| Inkling 2 Small | 83.3% | 2026-11-15 | independent | Source ↗ |
| Nova Premier | 34.3% | 2026-11-15 | independent | Source ↗ |
| Muse Wonder Full | 83.7% | 2026-11-15 | independent | Source ↗ |
| Cogito v2.1 | 22.7% | 2026-11-15 | independent | Source ↗ |
| Ring-2.6-1T | 70% | 2026-11-15 | independent | Source ↗ |
| Phi-4 | 0% | 2026-11-15 | independent | Source ↗ |
| Agnes 2.5 Pro Beta | 83% | 2026-11-15 | independent | Source ↗ |
| Jamba Reasoning 3B | 6.3% | 2026-11-15 | independent | Source ↗ |
| Quasar 438B | 76.3% | 2026-11-15 | independent | Source ↗ |
| LFM2 24B A2B | 0% | 2026-11-15 | independent | Source ↗ |
| KAT Coder Pro V2 | 73% | 2026-11-15 | independent | Source ↗ |
| Qwen3 Coder Next | 47% | 2026-11-15 | independent | Source ↗ |
Human Baseline & Difficulty Horizon
Calibrated human reference points, specialist benchmarks, and ceiling thresholds.No peer-reviewed human baseline has been published for this benchmark.
Metric & Scoring Methodology
Verification protocols, aggregation formulas, and specialized metric variants.accuracy (%)Dataset & Compute Cost
Evaluation volume, public availability, API pricing, and local hardware requirements.$5 – $20 USD for full benchmark evaluation run on frontier APIs.
1x NVIDIA RTX 4090 (24GB) or A100 (40GB/80GB) via vLLM / SGLang
How to Run & Reproduce
Standardized evaluation protocols, CLI commands, and reproducible runner templates.lm_eval --model hf --model_args pretrained=<model_path> --tasks aa-lcr --batch_size autoopencompass --datasets aa-lcr --models <model_config># Standard API Evaluation Loop
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": prompt}],
temperature=0.0,
)When publishing results for AA-LCR (Long Context Reasoning), always report the exact prompt template, few-shot exemplar ordering, sampling temperature (temperature=0), maximum reasoning budget tokens, and the precise timestamped model snapshot ID.
Contamination & Memorization Analysis
Audit of pretraining exposure risks, memorization vectors, and refresh policies.Static fixed snapshot
Public on web / HuggingFace