Model comparison
Kimi K2 (Jul 2025) vs Mistral Large
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 31.6 on the Noometry Index.
Last verified . 32 shared benchmarks.
Mistral AISummary
- They share 32 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 9 categories and Mistral Large in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 (Jul 2025) leads 40.1 to 17.1.
- The biggest single-benchmark swing is Omni-MATH: 65.4% for Kimi K2 (Jul 2025) and 28.1% for Mistral Large.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $2 / $6 for Mistral Large.
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 131K.
Side by side
| Kimi K2 (Jul 2025) | Mistral Large | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 40.9 | 31.6 |
| Released | 2025-07-12 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 262K | 16K |
| Input $ / M tokens | $0.57 | $2 |
| Output $ / M tokens | $2.30 | $6 |
| Results tracked | 42 | 51 |
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): 43.1 (#83), Mistral Large: 33.8 (#240)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large |
|---|---|---|
| LMArena Coding | 1399 | 1277 |
| ALE-Bench | 597.5 | 264.7 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| SciCode | — | 36.2% |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 32.2 (#59), Mistral Large: 28.4 (#83)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 59.1% | 38.4% |
| Terminal-Bench | 35.7% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 22.7 (#173), Mistral Large: 15.4 (#305)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large |
|---|---|---|
| SimpleBench | 26.3% | 22.5% |
| LMArena Hard Prompts | 1384 | 1257 |
| Epoch Capabilities Index | 146.02 | 128.52 |
| ForecastBench | 60.2 | 57.1 |
| Kagi LLM Benchmark | 64.4% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| LiveBench | — | 48.4% |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 40.1 (#81), Mistral Large: 17.1 (#285)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large |
|---|---|---|
| Omni-MATH | 65.4% | 28.1% |
| LMArena Math | 1396 | 1262 |
| FrontierMath (Feb 2025 set) | 21.4% | 0.3% |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 36.9 (#153), Mistral Large: 30.0 (#224)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large |
|---|---|---|
| MMLU-Pro | 81.9% | 59.9% |
| Confabulations | 20.4% | 21.4% |
| Vectara Hallucination Rate | 17.9% | 4.5% |
| GPQA (HELM) | 65.3% | 43.5% |
| LMArena Expert | 1363 | 1232 |
| GPQA Diamond | — | 51.3% |
| MMLU | — | 80% |
Multilingual Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 49.8 (#125), Mistral Large: 40.1 (#214)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large |
|---|---|---|
| LMArena Non-English | 1372 | 1237 |
| LMArena Chinese | 1416 | 1240 |
| LMArena French | 1379 | 1324 |
| LMArena German | 1386 | 1254 |
| LMArena Japanese | 1349 | 1187 |
| LMArena Korean | 1324 | 1202 |
| LMArena Russian | 1384 | 1257 |
| LMArena Spanish | 1383 | 1268 |
Instruction Following Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 71.3 (#151), Mistral Large: 68.1 (#186)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large |
|---|---|---|
| IFEval | 85% | 87.7% |
| LMArena Instruction Following | 1347 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 41.2 (#140), Mistral Large: 38.3 (#194)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1353 | 1262 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 62.5 (#76), Mistral Large: 40.9 (#237)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large |
|---|---|---|
| LMArena Text | 1380 | 1266 |
| LMArena Creative Writing | 1349 | 1243 |
| Short-Story Creative Writing | 85.6% | 69% |
| EQ-Bench Creative Writing | 1666 | 985 |
| WildBench | 86.2% | 80.1% |
| LMArena Multi-Turn | 1371 | 1260 |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Mistral Large?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 31.6 on the Noometry Index.
Which is cheaper, Kimi K2 (Jul 2025) or Mistral Large?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Mistral Large lists at $2 and $6.
Is Kimi K2 (Jul 2025) or Mistral Large better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 43.1 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Kimi K2 (Jul 2025) does, with 262K tokens against 131K.
How many benchmarks do Kimi K2 (Jul 2025) and Mistral Large share?
32 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Mistral Large has 51.