Model comparison
Kimi K3 vs Mistral Medium
Kimi K3 is the stronger model overall, scoring 59.5 to 36.3 on the Noometry Index. Mistral Medium 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 10 categories and Mistral Medium in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 28.1.
- The biggest single-benchmark swing is ProofBench: 87% for Kimi K3 and 9% for Mistral Medium.
- Mistral Medium is cheaper at $1.50 / $7.50 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 262K.
Side by side
| Kimi K3 | Mistral Medium | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 59.5 | 36.3 |
| Released | 2026-07-16 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 1.05M | 262K |
| Input $ / M tokens | $3 | $1.50 |
| Output $ / M tokens | $15 | $7.50 |
| Results tracked | 53 | 36 |
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 Medium: 34.2 (#243)
| Benchmark | Kimi K3 | Mistral Medium |
|---|---|---|
| FrontierCode | 44.2% | 8% |
| SciCode | 59.5% | 40.2% |
| WeirdML | 82.6% | 43.7% |
| LMArena Coding | 1508 | 1434 |
| ALE-Bench | 1,524 | 763.98 |
| DeepSWE | 68.5% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
Agentic & Tool Use Kimi K3 leads
Kimi K3: 41.8 (#20), Mistral Medium: 28.3 (#90)
| Benchmark | Kimi K3 | Mistral Medium |
|---|---|---|
| APEX-Agents | 50.6% | — |
| Berkeley Function Calling Leaderboard | — | 37.7% |
| 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 Medium: 24.0 (#167)
| Benchmark | Kimi K3 | Mistral Medium |
|---|---|---|
| CritPt | 23.4% | 0% |
| LMArena Hard Prompts | 1496 | 1426 |
| DTBench | 91.2% | 75.5% |
| LMCA | 52.7% | 26.1% |
| Surface Evolver Bench | 95% | 26.9% |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| Kagi LLM Benchmark | — | 50% |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| Chess Puzzles | 39% | — |
| Mystery Game Puzzles | 26% | — |
| Epoch Capabilities Index | 157.45 | — |
| ForecastBench | 61.1 | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Mistral Medium: 28.1 (#245)
| Benchmark | Kimi K3 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.2% | 32.2% |
| ProofBench | 87% | 9% |
| LMArena Math | 1491 | 1408 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Mistral Medium: 25.0 (#265)
| Benchmark | Kimi K3 | Mistral Medium |
|---|---|---|
| GPQA Diamond | 93.1% | 59.5% |
| LMArena Expert | 1521 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 50.6% | — |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Kimi K3 leads
Kimi K3: 37.8 (#70), Mistral Medium: 35.3 (#88)
| Benchmark | Kimi K3 | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Mistral Medium: 52.1 (#91)
| Benchmark | Kimi K3 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1466 | 1408 |
| LMArena Chinese | 1529 | 1447 |
| LMArena French | 1491 | 1459 |
| LMArena German | 1488 | 1432 |
| LMArena Japanese | 1487 | 1378 |
| LMArena Korean | 1458 | 1380 |
| LMArena Russian | 1482 | 1411 |
| LMArena Spanish | 1472 | 1433 |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Mistral Medium: 73.7 (#116)
| Benchmark | Kimi K3 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1483 | 1398 |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Mistral Medium: 42.9 (#114)
| Benchmark | Kimi K3 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1494 | 1406 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Mistral Medium: 60.0 (#103)
| Benchmark | Kimi K3 | Mistral Medium |
|---|---|---|
| LMArena Text | 1476 | 1424 |
| LMArena Creative Writing | 1454 | 1391 |
| LMArena Multi-Turn | 1488 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than Mistral Medium?
Kimi K3 is the stronger model overall, scoring 59.5 to 36.3 on the Noometry Index. Mistral Medium 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 Medium?
Mistral Medium is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or Mistral Medium better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 262K.
How many benchmarks do Kimi K3 and Mistral Medium share?
28 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Mistral Medium has 36.