Moonshot AIopen-weight
Released: 2026-10-23Artificial AnalysisKimi K3.1 Pro
OpenRouter ranked #9 foundation model processing 3.92T tokens weekly. Deployed by moonshotai.
Intelligence Index
46.5/ 100
Artificial Analysis Intelligence Index (independent composite)Throughput Speed
30tok/sec
Output streaming throughputTime to First Answer
179s
Time to first answer token, including any thinkingCost to Run the Index
3.68USD
Artificial Analysis cost of the full Index runMeasured results · Artificial Analysis
Independent evaluations of Kimi K3.1 Pro. Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.
- Intelligence Index
- 46.5
- Cost to run the Index
- $3.68
- Time per task
- 40.1 min
- Omniscience index
- 29.9
- Reasoning model
- Yes
- Cached-input price
- $0.2 / 1M
Reasoning & knowledge
- AA-Omniscience Accuracy48.9%
- CritPt24.6%
- CritPt v2 (Hard)49.5%
- HLE-Diamond37.3%
- Humanity's Last Exam52.5%
Coding & terminal agents
- FrontierCode 1.147.1%
- FrontierCode-AA 2.025.4%
- SciCode60.8%
- Terminal-Bench 4.067.2%
- Terminal-Bench-Science 0.134.3%
Agentic work
- AA-AnalystAgent38.8%
- AA-Briefcase v1.1 (Elo)1674 Elo
- AutomationBench-AA73.3%
- GDPval-AA (normalized Elo)1861 Elo
- Multimodal Knowledge Agent (MKA)43.9%
Long context & documents
Health & safety
Headline Evaluation Breakdown
Six independently measured evaluations (Artificial Analysis)Reasoning · CritPt v2 (Hard)49.5%
Coding & agents · Terminal-Bench 4.067.2%
Long context · AA-LCR86.3%
Knowledge · Humanity's Last Exam52.5%
Sourced Benchmark Evaluations (19)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| HLE-Diamond | Active | 37.3% | 93 | 2026-11-15 | independent | Source ↗ |
| VIALS-AA | Active | 45.3% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-AnalystAgent | Active | 38.8% | 93 | 2026-11-15 | independent | Source ↗ |
| AutomationBench-AA | Active | 73.3% | 93 | 2026-11-15 | independent | Source ↗ |
| Multimodal Knowledge Agent (MKA) | Active | 43.9% | 93 | 2026-11-15 | independent | Source ↗ |
| MLCR-AA (Medical Long Context Reasoning) | Active | 38.3% | 93 | 2026-11-15 | independent | Source ↗ |
| GDP.pdf | Active | 31.4% | 93 | 2026-11-15 | independent | Source ↗ |
| FrontierCode-AA 2.0 | Active | 25.5% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Non-Hallucination) | Active | 62.7% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Accuracy) | Active | 48.9% | 93 | 2026-11-15 | independent | Source ↗ |
| FrontierCode | Active | 47.1% | 98 | 2026-11-15 | independent | Source ↗ |
| CritPt v2 (Hard) | Active | 49.5% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt | Active | 24.6% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-LCR (Long Context Reasoning) | Active | 86.3% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench-Science 0.1 | Active | 34.3% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 4.0 | Active | 67.2% | 93 | 2026-11-15 | independent | Source ↗ |
| SciCode | Active | 60.8% | 93 | 2026-11-15 | independent | Source ↗ |
| MMMU-Pro | Active | 83.9% | 93 | 2026-11-15 | independent | Source ↗ |
| Humanity's Last Exam | Active | 52.5% | 93 | 2026-11-15 | independent | Source ↗ |
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run kimi-k3-1-pro
# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k3-1-pro",
"messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
}'Evaluation & Sourcing Notes
Scores listed for Kimi K3.1 Pro represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.