Moonshot AI
availableShows if the model has enough results for an index.Kimi K2.7 Code
Kimi K2.7 Code is a reasoning model from Moonshot AI. 34 benchmarks count toward its score, in 6 categories.
IndexOverall score. 50 is the middle.59.5 ±4.3
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.58/s
Input / 1MUS dollars per 1M input tokens.$0.706
Output / 1MUS dollars per 1M output tokens.$3.21
ContextMaximum tokens in one request.262K
EloLMArena rating and rank.N/A
50 is the middle of the board. The range shows the doubt in the index.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
34 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | Math | 95.6% | 65.0 | — | — | Epoch AI |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 90.1% | 63.5 | — | — | Victor Barres et al. |
| Artificial Analysis GPQA Diamond | Knowledge | 89.6% | 60.4 | — | — | Artificial Analysis |
| GPQA diamond | Knowledge | 87.9% | 59.4 | — | — | Epoch AI |
| LiveBench Reasoning | Reasoning | 82.8% | 71.0 | — | 25 Jun 2026 | LiveBench |
| LiveCodeBench | Coding | 82.0% | 58.9 | — | 1 Sept 2026 | Vals AI |
| MCPMark-Verified | Agentic | 81.1% | — | — | — | MCPMark |
| LiveBench Mathematics | Math | 79.6% | 54.2 | — | 25 Jun 2026 | LiveBench |
| Artificial Analysis Long Context Reasoning | Reasoning | 79.3% | 63.1 | — | — | Artificial Analysis |
| SWE-bench | Coding | 78.2% | 60.3 | — | 1 Sept 2026 | Vals AI |
| LiveBench Language | Knowledge | 77.9% | 64.6 | — | 25 Jun 2026 | LiveBench |
| MCP Atlas | Agentic | 76.0% | 65.4 | — | — | OpenAI |
| LiveBench Coding | Coding | 74.0% | 60.5 | — | 25 Jun 2026 | LiveBench |
| Terminal-Bench 2.1 | Agentic | 67.0% | 63.6 | — | 21 Sept 2026 | Vals AI |
| Artificial Analysis IFBench | Instruction | 63.1% | 53.1 | — | — | Artificial Analysis |
| LiveBench Data Analysis | Reasoning | 62.7% | 43.0 | — | 25 Jun 2026 | LiveBench |
| Kimi Code Bench v2 | Coding | 62.0% | — | — | — | Moonshot AI |
| Artificial Analysis Coding Index | Coding | 60.8% | 61.8 | — | — | Artificial Analysis |
| LiveBench Instruction Following | Instruction | 56.3% | 49.1 | — | 25 Jun 2026 | LiveBench |
| FrontierMath-Tiers-1-3-v2-Private | Math | 54.0% | 61.9 | — | — | Epoch AI |
| ProgramBench: Can Language Models Rebuild Programs From Scratch? | Coding | 53.6% | 58.5 | — | — | John Yang et al. |
| OpenHarmony Bench v1.0 | Coding | 52.1% | 60.9 | — | — | OpenHarmony Bench authors |
| SkillsBench | Coding | 50.0% | 65.4 | OpenHands | 11 Sept 2026 | Vals AI |
| cursorBench32 | Coding | 49.7% | 58.9 | — | — | Benchmark authors |
| Artificial Analysis SciCode | Coding | 47.8% | 59.2 | — | — | Artificial Analysis |
| Vibe Code Bench v1.1 | Coding | 47.2% | 61.8 | OpenHands | 21 Sept 2026 | Vals AI |
| Kimi Claw 24/7 Bench | Agentic | 46.9% | — | — | — | Moonshot AI |
| LiveBench Agentic Coding | Agentic | 45.7% | 59.7 | — | 25 Jun 2026 | LiveBench |
| Artificial Analysis Omniscience Accuracy | Knowledge | 39.6% | 62.9 | — | — | Artificial Analysis |
| SimpleQA Verified | Knowledge | 36.5% | 55.3 | — | — | Epoch AI |
| MLS-Bench Lite | Coding | 35.1% | — | — | — | MLS-Bench |
| Artificial Analysis Humanity's Last Exam | Knowledge | 35.0% | 62.5 | — | — | Artificial Analysis |
| GDPval-AA normalized | Agentic | 26.3% | 55.8 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 25.8% | 54.7 | — | — | Artificial Analysis |
| Code Migration | Coding | 25.4% | 61.2 | — | 21 Sept 2026 | Vals AI |
| Artificial Analysis Agentic Index | Agentic | 22.5% | 55.5 | — | — | Artificial Analysis |
| Chess Puzzles | Reasoning | 21.0% | 50.7 | — | — | Epoch AI |
| FrontierMath-Tier-4-v2-Private | Math | 12.2% | 53.8 | — | — | Epoch AI |
| Critical Physics Tasks | Reasoning | 10.0% | 59.3 | — | — | Artificial Analysis |
| ProgramBench | Coding | 0.0% | — | — | 21 Sept 2026 | Vals AI |
34 benchmarks count, from 35 of 40 results. A grey row does not count. Too few models took that benchmark.