Model comparison
Kimi K3 vs Mistral Large
Kimi K3 is the stronger model overall, scoring 59.5 to 31.9 on the Noometry Index. Mistral Large costs 2.0× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
Mistral AISummary
- They share 28 benchmarks with published results for both. Kimi K3 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 K3 leads 74.2 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 97.2% for Kimi K3 and 8.5% for Mistral Large.
- Mistral Large is cheaper at $2 / $6 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 131K.
Side by side
| Kimi K3 | Mistral Large | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 59.5 | 31.9 |
| Released | 2026-07-16 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 1.05M | 131K |
| Max output | 1.05M | 16K |
| Input $ / M tokens | $3 | $2 |
| Output $ / M tokens | $15 | $6 |
| Results tracked | 53 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), Mistral Large: 34.3 (#240)
| Benchmark | Kimi K3 | Mistral Large |
|---|---|---|
| SciCode | 59.5% | 36.2% |
| LMArena Coding | 1508 | 1277 |
| ALE-Bench | 1,524 | 264.7 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| WeirdML | 82.6% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Kimi K3 leads
Kimi K3: 41.8 (#20), Mistral Large: 28.6 (#89)
| Benchmark | Kimi K3 | Mistral Large |
|---|---|---|
| APEX-Agents | 50.6% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Mistral Large: 15.8 (#310)
| Benchmark | Kimi K3 | Mistral Large |
|---|---|---|
| SimpleBench | 60.7% | 22.5% |
| CritPt | 23.4% | 0% |
| LMArena Hard Prompts | 1496 | 1257 |
| DTBench | 91.2% | 65.1% |
| LMCA | 52.7% | 16.7% |
| Epoch Capabilities Index | 157.45 | 128.52 |
| ForecastBench | 61.1 | 57.1 |
| ARC-AGI-2 | 60.4% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| Chess Puzzles | 39% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 26% | — |
| LiveBench Data Analysis | — | 50.1% |
| Surface Evolver Bench | 95% | — |
| LiveBench | — | 48.4% |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Mistral Large: 18.2 (#291)
| Benchmark | Kimi K3 | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.2% | 8.5% |
| LMArena Math | 1491 | 1262 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| ProofBench | 87% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Mistral Large: 30.1 (#230)
| Benchmark | Kimi K3 | Mistral Large |
|---|---|---|
| GPQA Diamond | 93.1% | 51.3% |
| LMArena Expert | 1521 | 1232 |
| SimpleQA Verified | 50.6% | — |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multimodal Not comparable
Kimi K3: 37.8 (#70), Mistral Large: —
| Benchmark | Kimi K3 | Mistral Large |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Mistral Large: 40.0 (#219)
| Benchmark | Kimi K3 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1466 | 1237 |
| LMArena Chinese | 1529 | 1240 |
| LMArena French | 1491 | 1325 |
| LMArena German | 1488 | 1254 |
| LMArena Japanese | 1487 | 1188 |
| LMArena Korean | 1458 | 1202 |
| LMArena Russian | 1482 | 1257 |
| LMArena Spanish | 1472 | 1268 |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Mistral Large: 67.9 (#191)
| Benchmark | Kimi K3 | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1483 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Mistral Large: 38.3 (#199)
| Benchmark | Kimi K3 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1494 | 1261 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Mistral Large: 40.7 (#242)
| Benchmark | Kimi K3 | Mistral Large |
|---|---|---|
| LMArena Text | 1476 | 1266 |
| LMArena Creative Writing | 1454 | 1243 |
| EQ-Bench Creative Writing | 2082 | 985 |
| LMArena Multi-Turn | 1488 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| EQ-Bench 4 | 1339 | — |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Kimi K3 better than Mistral Large?
Kimi K3 is the stronger model overall, scoring 59.5 to 31.9 on the Noometry Index. Mistral Large costs 2.0× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Kimi K3 or Mistral Large?
Mistral Large is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or Mistral Large better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 131K.
How many benchmarks do Kimi K3 and Mistral Large share?
28 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Mistral Large has 51.