Model comparison
Kimi K2 (Jul 2025) vs Mistral Medium
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 36.3 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AISummary
- They share 24 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 5 categories and Mistral Medium in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 (Jul 2025) leads 42.7 to 28.1.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 59.1% for Kimi K2 (Jul 2025) and 37.7% for Mistral Medium.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
Side by side
| Kimi K2 (Jul 2025) | Mistral Medium | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 41.2 | 36.3 |
| Released | 2025-07-12 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 262K |
| Input $ / M tokens | $0.57 | $1.50 |
| Output $ / M tokens | $2.30 | $7.50 |
| Results tracked | 42 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.4 (#102), Mistral Medium: 34.2 (#243)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Medium |
|---|---|---|
| WeirdML | 42.8% | 43.7% |
| LMArena Coding | 1399 | 1434 |
| ALE-Bench | 597.5 | 763.98 |
| FrontierCode | — | 8% |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| SciCode | — | 40.2% |
| GSO | 4.9% | — |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 32.4 (#64), Mistral Medium: 28.3 (#90)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 59.1% | 37.7% |
| Terminal-Bench | 35.7% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Too close to call
Kimi K2 (Jul 2025): 23.3 (#179), Mistral Medium: 24.0 (#167)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 64.4% | 50% |
| LMArena Hard Prompts | 1384 | 1426 |
| SimpleBench | 26.3% | — |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 146.01 | — |
| ForecastBench | 60.2 | — |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.7 (#83), Mistral Medium: 28.1 (#245)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Medium |
|---|---|---|
| LMArena Math | 1397 | 1408 |
| FrontierMath (Feb 2025 set) | 21.4% | 0.3% |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| Omni-MATH | 65.4% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 37.3 (#157), Mistral Medium: 25.0 (#265)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Medium |
|---|---|---|
| Vectara Hallucination Rate | 17.9% | 22.7% |
| LMArena Expert | 1365 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| GPQA (HELM) | 65.3% | — |
Multimodal Not comparable
Kimi K2 (Jul 2025): —, Mistral Medium: 35.3 (#88)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Kimi K2 (Jul 2025): 49.6 (#130), Mistral Medium: 52.1 (#91)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1372 | 1408 |
| LMArena Chinese | 1415 | 1447 |
| LMArena French | 1379 | 1459 |
| LMArena German | 1387 | 1432 |
| LMArena Japanese | 1349 | 1378 |
| LMArena Korean | 1325 | 1380 |
| LMArena Russian | 1385 | 1411 |
| LMArena Spanish | 1386 | 1433 |
Instruction Following Mistral Medium leads
Kimi K2 (Jul 2025): 71.1 (#156), Mistral Medium: 73.7 (#116)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1348 | 1398 |
| IFEval | 85% | — |
Long Context Mistral Medium leads
Kimi K2 (Jul 2025): 41.2 (#145), Mistral Medium: 42.9 (#114)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1353 | 1406 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 62.3 (#78), Mistral Medium: 60.0 (#103)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Medium |
|---|---|---|
| LMArena Text | 1380 | 1424 |
| LMArena Creative Writing | 1350 | 1391 |
| Short-Story Creative Writing | 85.6% | 77.3% |
| LMArena Multi-Turn | 1371 | 1418 |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Mistral Medium?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 36.3 on the Noometry Index.
Which is cheaper, Kimi K2 (Jul 2025) or Mistral Medium?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Kimi K2 (Jul 2025) or Mistral Medium better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Kimi K2 (Jul 2025) and Mistral Medium share?
24 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Mistral Medium has 36.