Up to four models
Kimi K2.6 vs Mistral Large 4
On the index (GPT-4 = 100), Kimi K2.6 scores 152 and Mistral Large 4 148. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Kimi K2.6
152136–169
WeightsOpen
ReleasedApr 2026
Price in / out$0.65 / $3.41
Context262K
Core tests taken4 of 9
148132–165
WeightsOpen
ReleasedOct 2026
Price in / out$0.70 / $2.1
Context1.05M
Core tests taken3 of 9
Kimi K2.6 and Mistral Large 4 are too close to call (4 points apart, within the uncertainty), ahead on 1 of 2 shared core tests, at a similar price.
Test by testthird-party results
Kimi K2.6
Mistral Large 4
Every result as a table
| Test | Kimi K2.6 | Mistral Large 4 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 90.8% | 88.1% |
| SimpleQA Verified | 34.9% | 20.0% |
| Maths | ||
| FrontierMath (tiers 1-3) | 57.2% | 58.6% |
| AIME-style maths (OTIS mock) | 96.1% | 98.3% |
| Chess puzzles | 20.0% | 33.0% |
| FrontierMath (tier 4) | 25.6% | 26.8% |
| Agents | ||
| DTBench | 90.9% | 88.2% |
| Furniture assembly | 21.7% | 20.8% |
| LMCA | 37.3% | 35.8% |
| Mystery game puzzles | 18.0% | 17.0% |
Tests at least two of these models have taken. Bold rows are the core tests.