Model comparison
Kimi K2 Thinking Turbo vs o3
o3 is the stronger model overall, scoring 47.5 to 45.8 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 2 categories and o3 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3 leads 53.3 to 43.2.
- The biggest single-benchmark swing is Chess Puzzles: 20% for Kimi K2 Thinking Turbo and 38% for o3.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.
Side by side
| Kimi K2 Thinking Turbo | o3 | |
|---|---|---|
| Provider | Moonshot AI | OpenAI |
| Noometry Index | 45.8 | 47.5 |
| Released | 2025-11-06 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 21 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Kimi K2 Thinking Turbo: 38.4 (#178), o3: 46.8 (#64)
| Benchmark | Kimi K2 Thinking Turbo | o3 |
|---|---|---|
| LMArena Coding | 1454 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| LMArena WebDev | 1322 | — |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use Not comparable
Kimi K2 Thinking Turbo: —, o3: 34.5 (#44)
| Benchmark | Kimi K2 Thinking Turbo | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning Too close to call
Kimi K2 Thinking Turbo: 32.5 (#75), o3: 32.0 (#78)
| Benchmark | Kimi K2 Thinking Turbo | o3 |
|---|---|---|
| Chess Puzzles | 20% | 38% |
| LMArena Hard Prompts | 1428 | 1402 |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| Epoch Capabilities Index | — | 146.86 |
| ForecastBench | — | 62.5 |
Math o3 leads
Kimi K2 Thinking Turbo: 47.4 (#68), o3: 50.2 (#58)
| Benchmark | Kimi K2 Thinking Turbo | o3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.1% | 84.4% |
| LMArena Math | 1429 | 1426 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Kimi K2 Thinking Turbo: 50.9 (#69), o3: 54.6 (#52)
| Benchmark | Kimi K2 Thinking Turbo | o3 |
|---|---|---|
| GPQA Diamond | 84.2% | 81.8% |
| LMArena Expert | 1439 | 1402 |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
Multimodal Not comparable
Kimi K2 Thinking Turbo: —, o3: 41.4 (#36)
| Benchmark | Kimi K2 Thinking Turbo | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual Too close to call
Kimi K2 Thinking Turbo: 51.4 (#109), o3: 51.7 (#105)
| Benchmark | Kimi K2 Thinking Turbo | o3 |
|---|---|---|
| LMArena Non-English | 1398 | 1401 |
| LMArena Chinese | 1456 | 1437 |
| LMArena French | 1425 | 1430 |
| LMArena German | 1390 | 1420 |
| LMArena Japanese | 1357 | 1403 |
| LMArena Korean | 1330 | 1370 |
| LMArena Russian | 1391 | 1406 |
| LMArena Spanish | 1406 | 1395 |
Instruction Following Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 74.0 (#109), o3: 72.8 (#127)
| Benchmark | Kimi K2 Thinking Turbo | o3 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
Kimi K2 Thinking Turbo: 43.2 (#102), o3: 53.3 (#6)
| Benchmark | Kimi K2 Thinking Turbo | o3 |
|---|---|---|
| LMArena Longer Query | 1415 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
Kimi K2 Thinking Turbo: 60.0 (#104), o3: 63.5 (#64)
| Benchmark | Kimi K2 Thinking Turbo | o3 |
|---|---|---|
| LMArena Text | 1415 | 1410 |
| LMArena Creative Writing | 1374 | 1359 |
| LMArena Multi-Turn | 1414 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than o3?
o3 is the stronger model overall, scoring 47.5 to 45.8 on the Noometry Index.
Is Kimi K2 Thinking Turbo or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 38.4 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and o3 share?
20 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and o3 has 63.