Model comparison
Kimi K2 Thinking Turbo vs o3-mini
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 36.7 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 6 categories and o3-mini in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 Thinking Turbo leads 45.5 to 27.6.
- The biggest single-benchmark swing is GPQA Diamond: 84.2% for Kimi K2 Thinking Turbo and 77% for o3-mini.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.
Side by side
| Kimi K2 Thinking Turbo | o3-mini | |
|---|---|---|
| Provider | Moonshot AI | OpenAI |
| Noometry Index | 45.4 | 36.7 |
| Released | 2025-11-06 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 21 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Kimi K2 Thinking Turbo: 38.1 (#166), o3-mini: 41.4 (#116)
| Benchmark | Kimi K2 Thinking Turbo | o3-mini |
|---|---|---|
| LMArena Coding | 1454 | 1378 |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1322 | — |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
Agentic & Tool Use Not comparable
Kimi K2 Thinking Turbo: —, o3-mini: 29.3 (#79)
| Benchmark | Kimi K2 Thinking Turbo | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
Reasoning Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 31.4 (#72), o3-mini: 16.3 (#295)
| Benchmark | Kimi K2 Thinking Turbo | o3-mini |
|---|---|---|
| Chess Puzzles | 20% | 17% |
| LMArena Hard Prompts | 1428 | 1366 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| Epoch Capabilities Index | — | 140.35 |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 45.5 (#62), o3-mini: 27.6 (#236)
| Benchmark | Kimi K2 Thinking Turbo | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.1% | 76.9% |
| LMArena Math | 1429 | 1396 |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 50.9 (#64), o3-mini: 38.3 (#135)
| Benchmark | Kimi K2 Thinking Turbo | o3-mini |
|---|---|---|
| GPQA Diamond | 84.2% | 77% |
| LMArena Expert | 1439 | 1364 |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
Multilingual Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 51.6 (#104), o3-mini: 45.9 (#159)
| Benchmark | Kimi K2 Thinking Turbo | o3-mini |
|---|---|---|
| LMArena Non-English | 1398 | 1319 |
| LMArena Chinese | 1457 | 1379 |
| LMArena French | 1425 | 1333 |
| LMArena German | 1390 | 1303 |
| LMArena Japanese | 1356 | 1286 |
| LMArena Korean | 1329 | 1314 |
| LMArena Russian | 1390 | 1304 |
| LMArena Spanish | 1407 | 1321 |
Instruction Following o3-mini leads
Kimi K2 Thinking Turbo: 74.2 (#103), o3-mini: 75.3 (#67)
| Benchmark | Kimi K2 Thinking Turbo | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1403 | 1338 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 43.2 (#99), o3-mini: 33.8 (#251)
| Benchmark | Kimi K2 Thinking Turbo | o3-mini |
|---|---|---|
| LMArena Longer Query | 1415 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 60.2 (#99), o3-mini: 50.4 (#177)
| Benchmark | Kimi K2 Thinking Turbo | o3-mini |
|---|---|---|
| LMArena Text | 1415 | 1337 |
| LMArena Creative Writing | 1373 | 1286 |
| LMArena Multi-Turn | 1414 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than o3-mini?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 36.7 on the Noometry Index.
Is Kimi K2 Thinking Turbo or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 41.4 versus 38.1 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and o3-mini share?
20 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and o3-mini has 51.