Up to four models
Claude Opus 4.5 vs Mistral Large 4
On the index (GPT-4 = 100), Claude Opus 4.5 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.
Claude Opus 4.5
152136–168
WeightsClosed
ReleasedNov 2025
Price in / out$5.0 / $25
Context200K
Core tests taken5 of 9
148132–165
WeightsOpen
ReleasedOct 2026
Price in / out$0.70 / $2.1
Context1.05M
Core tests taken3 of 9
Claude Opus 4.5 and Mistral Large 4 are too close to call (4 points apart, within the uncertainty), ahead on 0 of 2 shared core tests, at 9.5× the price.
Test by testthird-party results
Claude Opus 4.5
Mistral Large 4
Every result as a table
| Test | Claude Opus 4.5 | Mistral Large 4 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 86.1% | 88.1% |
| SimpleQA Verified | 45.7% | 20.0% |
| Maths | ||
| FrontierMath (tiers 1-3) | 34.4% | 58.6% |
| AIME-style maths (OTIS mock) | 86.1% | 98.3% |
| Chess puzzles | 14.0% | 33.0% |
| FrontierMath (tier 4) | 4.9% | 26.8% |
| Agents | ||
| DTBench | 89.9% | 88.2% |
| Furniture assembly | 28.3% | 20.8% |
| LMCA | 44.5% | 35.8% |
| Mystery game puzzles | 22.0% | 17.0% |
Task length · METR45 sec
Tests at least two of these models have taken. Bold rows are the core tests.