Model comparison
Kimi K2 (Jul 2025) vs Mistral Large 3
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 39.1 on the Noometry Index. Mistral Large 3 costs 2.7× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 5 categories and Mistral Large 3 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2 (Jul 2025) leads 23.3 to 15.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 64.4% for Kimi K2 (Jul 2025) and 50.9% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
Side by side
| Kimi K2 (Jul 2025) | Mistral Large 3 | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 41.2 | 39.1 |
| Released | 2025-07-12 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 8K |
| Input $ / M tokens | $0.57 | $0.25 |
| Output $ / M tokens | $2.30 | $0.75 |
| Results tracked | 42 | 24 |
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 Large 3: 34.4 (#237)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1399 | 1448 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| LMArena WebDev | — | 1230 |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| ALE-Bench | 597.5 | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.4 (#64), Mistral Large 3: —
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large 3 |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 23.3 (#179), Mistral Large 3: 15.2 (#319)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 64.4% | 50.9% |
| LMArena Hard Prompts | 1384 | 1429 |
| SimpleBench | 26.3% | — |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |
| Epoch Capabilities Index | 146.01 | — |
| ForecastBench | 60.2 | — |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.7 (#83), Mistral Large 3: 38.7 (#129)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1397 | 1414 |
| Omni-MATH | 65.4% | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 37.3 (#157), Mistral Large 3: 36.0 (#177)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 17.9% | 14.5% |
| LMArena Expert | 1365 | 1421 |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| GPQA (HELM) | 65.3% | — |
Multimodal Not comparable
Kimi K2 (Jul 2025): —, Mistral Large 3: 38.2 (#66)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
Kimi K2 (Jul 2025): 49.6 (#130), Mistral Large 3: 52.5 (#84)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1372 | 1413 |
| LMArena Chinese | 1415 | 1447 |
| LMArena French | 1379 | 1455 |
| LMArena German | 1387 | 1437 |
| LMArena Japanese | 1349 | 1394 |
| LMArena Korean | 1325 | 1384 |
| LMArena Russian | 1385 | 1411 |
| LMArena Spanish | 1386 | 1440 |
Instruction Following Mistral Large 3 leads
Kimi K2 (Jul 2025): 71.1 (#156), Mistral Large 3: 74.0 (#108)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1348 | 1403 |
| IFEval | 85% | — |
Long Context Mistral Large 3 leads
Kimi K2 (Jul 2025): 41.2 (#145), Mistral Large 3: 43.1 (#105)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1353 | 1413 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 62.3 (#78), Mistral Large 3: 60.0 (#101)
| Benchmark | Kimi K2 (Jul 2025) | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1380 | 1428 |
| LMArena Creative Writing | 1350 | 1386 |
| EQ-Bench Creative Writing | 1666 | 1412 |
| LMArena Multi-Turn | 1371 | 1429 |
| Short-Story Creative Writing | 85.6% | — |
| WildBench | 86.2% | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Mistral Large 3?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 39.1 on the Noometry Index. Mistral Large 3 costs 2.7× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.
Which is cheaper, Kimi K2 (Jul 2025) or Mistral Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.
Is Kimi K2 (Jul 2025) or Mistral Large 3 better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 34.4 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 Large 3 share?
20 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Mistral Large 3 has 24.