Model comparison
Kimi K2 Thinking Turbo vs Mistral Medium
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 36.3 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 6 categories and Mistral Medium in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.1% for Kimi K2 Thinking Turbo and 32.2% for Mistral Medium.
Side by side
| Kimi K2 Thinking Turbo | Mistral Medium | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 45.8 | 36.3 |
| Released | 2025-11-06 | 2023-12-11 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 21 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 38.4 (#178), Mistral Medium: 34.2 (#243)
| Benchmark | Kimi K2 Thinking Turbo | Mistral Medium |
|---|---|---|
| LMArena Coding | 1454 | 1434 |
| FrontierCode | — | 8% |
| LMArena WebDev | 1322 | — |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Not comparable
Kimi K2 Thinking Turbo: —, Mistral Medium: 28.3 (#90)
| Benchmark | Kimi K2 Thinking Turbo | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 32.5 (#75), Mistral Medium: 24.0 (#167)
| Benchmark | Kimi K2 Thinking Turbo | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| Chess Puzzles | 20% | — |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 47.4 (#68), Mistral Medium: 28.1 (#245)
| Benchmark | Kimi K2 Thinking Turbo | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.1% | 32.2% |
| LMArena Math | 1429 | 1408 |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 50.9 (#69), Mistral Medium: 25.0 (#265)
| Benchmark | Kimi K2 Thinking Turbo | Mistral Medium |
|---|---|---|
| GPQA Diamond | 84.2% | 59.5% |
| LMArena Expert | 1439 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Not comparable
Kimi K2 Thinking Turbo: —, Mistral Medium: 35.3 (#88)
| Benchmark | Kimi K2 Thinking Turbo | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Too close to call
Kimi K2 Thinking Turbo: 51.4 (#109), Mistral Medium: 52.1 (#91)
| Benchmark | Kimi K2 Thinking Turbo | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1398 | 1408 |
| LMArena Chinese | 1456 | 1447 |
| LMArena French | 1425 | 1459 |
| LMArena German | 1390 | 1432 |
| LMArena Japanese | 1357 | 1378 |
| LMArena Korean | 1330 | 1380 |
| LMArena Russian | 1391 | 1411 |
| LMArena Spanish | 1406 | 1433 |
Instruction Following Too close to call
Kimi K2 Thinking Turbo: 74.0 (#109), Mistral Medium: 73.7 (#116)
| Benchmark | Kimi K2 Thinking Turbo | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1403 | 1398 |
Long Context Too close to call
Kimi K2 Thinking Turbo: 43.2 (#102), Mistral Medium: 42.9 (#114)
| Benchmark | Kimi K2 Thinking Turbo | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1415 | 1406 |
Writing & Preference Too close to call
Kimi K2 Thinking Turbo: 60.0 (#104), Mistral Medium: 60.0 (#103)
| Benchmark | Kimi K2 Thinking Turbo | Mistral Medium |
|---|---|---|
| LMArena Text | 1415 | 1424 |
| LMArena Creative Writing | 1374 | 1391 |
| LMArena Multi-Turn | 1414 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than Mistral Medium?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 36.3 on the Noometry Index.
Is Kimi K2 Thinking Turbo or Mistral Medium better for coding?
Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.4 versus 34.2 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and Mistral Medium share?
19 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Mistral Medium has 36.