Moonshot · model
Kimi K2 benchmark scores
As of 2026-10-07, Kimi K2 (Moonshot) has measured scores on 10 benchmarks and estimated scores on 38 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 76.6% | measured |
| AA-HLE | 7.4% | measured |
| AIME26 | 95.5% | estimated ± 0.6 pp, low confidence |
| Artificial Analysis Intelligence Index | 12.7% | measured |
| CritPt | 0.0% | measured |
| GDPval-AA | 3.2% | estimated ± 12.5 pp, low confidence |
| GPQA Diamond | 71.9% | estimated ± 2.2 pp, high confidence |
| HLE | 19.0% | estimated ± 9.5 pp, medium confidence |
| IFBench | 56.0% | estimated ± 6.9 pp, low confidence |
| AA-LCR | 53.0% | measured |
| AA-Omniscience Accuracy | 27.4% | measured |
| IFEval | 89.1% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 0.0% | estimated ± 5.9 pp, low confidence |
| τ²-bench results | 61.1% | measured |
| APEX-Agents-AA | 1.6% | estimated ± 11.4 pp, low confidence |
| BioMysteryBench (human-difficult) | 33.1% | estimated ± 5.9 pp, low confidence |
| BFCL v4 | 47.6% | estimated ± 9.8 pp, low confidence |
| AA Agentic Index | 12.0% | estimated ± 12.3 pp, low confidence |
| MMLU-Pro | 85.6% | estimated ± 3.5 pp, high confidence |
| FrontierMath v2 (Tier 4) | 0.0% | measured |
| FrontierMath v2 (Tiers 1-3) | 21.4% | measured |
| GPQA | 73.0% | estimated ± 3.2 pp, high confidence |
| AA-IFBench | 41.5% | measured |
| AA EnterpriseOps-Gym | 6.1% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-1 | 8.4% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-2 | 2.7% | estimated ± 14.2 pp, low confidence |
| Vals GPQA Diamond | 67.3% | estimated ± 7.4 pp, medium confidence |
| Vals MMLU-Pro | 84.5% | estimated ± 2.2 pp, high confidence |
| AA ITBench | 83.2% | estimated ± 3.6 pp, low confidence |
| HLE w/o tools | 5.9% | estimated ± 5.7 pp, low confidence |
| C-Eval | 86.6% | estimated ± 1.0 pp, low confidence |
| HMMT Nov 2025 | 99.9% | estimated ± 2.6 pp, low confidence |
| MCP-Tasks | 87.9% | estimated ± 8.2 pp, low confidence |
| MMAnswerBench | 81.9% | estimated ± 1.3 pp, low confidence |
| MMLU-Redux | 95.0% | estimated ± 1.1 pp, medium confidence |
| SuperGPQA | 72.3% | estimated ± 7.5 pp, medium confidence |
| HealthBench Hard | 0.6% | estimated ± 7.7 pp, low confidence |
| MMLU-Pro (Arcee) | 77.1% | estimated ± 4.0 pp, low confidence |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, medium confidence |
| FrontierMath (legacy) | 22.3% | estimated ± 0.7 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 11.4% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 57.7% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 25.1% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 58.5% | estimated ± 1.8 pp, low confidence |
| MMLU | 89.9% | estimated ± 1.1 pp, medium confidence |