Model comparison
Kimi K2.7 Code vs o1-mini
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 34.0 on the Noometry Index.
Last verified . 5 shared benchmarks.
Summary
- They share 5 benchmarks with published results for both. Kimi K2.7 Code scores higher in 4 categories and o1-mini in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.7 Code leads 39.0 to 8.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Kimi K2.7 Code and 46.9% for o1-mini.
- Kimi K2.7 Code has downloadable open weights; the other is API-only.
Side by side
| Kimi K2.7 Code | o1-mini | |
|---|---|---|
| Provider | Moonshot AI | OpenAI |
| Noometry Index | 43.3 | 34.0 |
| Released | 2026-06-12 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.95 | — |
| Output $ / M tokens | $4 | — |
| Results tracked | 19 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.7 Code leads
Kimi K2.7 Code: 42.9 (#95), o1-mini: 35.5 (#224)
| Benchmark | Kimi K2.7 Code | o1-mini |
|---|---|---|
| WeirdML | 54.1% | 36.3% |
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1473 | — |
| SciCode | 47.5% | — |
| LiveBench Coding | — | 48% |
| LMArena Coding | — | 1362 |
| ALE-Bench | 886.23 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Too close to call
Kimi K2.7 Code: 24.0 (#122), o1-mini: 24.6 (#118)
| Benchmark | Kimi K2.7 Code | o1-mini |
|---|---|---|
| APEX-Agents | 37.6% | — |
| Cybench | — | 10% |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |
Reasoning Kimi K2.7 Code leads
Kimi K2.7 Code: 39.0 (#61), o1-mini: 8.8 (#346)
| Benchmark | Kimi K2.7 Code | o1-mini |
|---|---|---|
| SimpleBench | 57.9% | 18.1% |
| Epoch Capabilities Index | 149.97 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| ARC-AGI-1 | — | 14% |
| CritPt | 10% | — |
| Chess Puzzles | 21% | — |
| LiveBench Reasoning | — | 72.3% |
| LMArena Hard Prompts | — | 1333 |
| LiveBench Data Analysis | — | 57.9% |
| Surface Evolver Bench | 48.8% | — |
| LiveBench | — | 57.8% |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.9 (#48), o1-mini: 35.4 (#186)
| Benchmark | Kimi K2.7 Code | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 46.9% |
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| LiveBench Math | — | 62% |
| LMArena Math | — | 1358 |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Kimi K2.7 Code leads
Kimi K2.7 Code: 53.5 (#57), o1-mini: 34.9 (#192)
| Benchmark | Kimi K2.7 Code | o1-mini |
|---|---|---|
| GPQA Diamond | 87.9% | 62.4% |
| SimpleQA Verified | 36.5% | — |
| Confabulations | — | 18.6% |
| LMArena Expert | — | 1316 |
Multilingual Not comparable
Kimi K2.7 Code: —, o1-mini: 43.6 (#182)
| Benchmark | Kimi K2.7 Code | o1-mini |
|---|---|---|
| LMArena Non-English | — | 1289 |
| LMArena Chinese | — | 1314 |
| LMArena French | — | 1293 |
| LMArena German | — | 1278 |
| LMArena Japanese | — | 1245 |
| LMArena Korean | — | 1223 |
| LMArena Russian | — | 1283 |
| LMArena Spanish | — | 1303 |
Instruction Following Not comparable
Kimi K2.7 Code: —, o1-mini: 66.7 (#206)
| Benchmark | Kimi K2.7 Code | o1-mini |
|---|---|---|
| LiveBench Instruction Following | — | 65.4% |
| LMArena Instruction Following | — | 1304 |
Long Context Not comparable
Kimi K2.7 Code: —, o1-mini: 40.1 (#161)
| Benchmark | Kimi K2.7 Code | o1-mini |
|---|---|---|
| LMArena Longer Query | — | 1320 |
Writing & Preference Not comparable
Kimi K2.7 Code: —, o1-mini: 48.4 (#202)
| Benchmark | Kimi K2.7 Code | o1-mini |
|---|---|---|
| LMArena Text | — | 1317 |
| LMArena Creative Writing | — | 1244 |
| Short-Story Creative Writing | — | 64.9% |
| LMArena Multi-Turn | — | 1314 |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Kimi K2.7 Code better than o1-mini?
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 34.0 on the Noometry Index.
Is Kimi K2.7 Code or o1-mini better for coding?
Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 35.5 in the Noometry coding category.
How many benchmarks do Kimi K2.7 Code and o1-mini share?
5 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and o1-mini has 39.