Compare / Claude Opus 4.8 vs Mistral Medium 3.5
Claude Opus 4.8 vs Mistral Medium 3.5
26 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Opus 4.8 | Mistral Medium 3.5 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | 0.04 | -0.16 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | 0.15 | -0.15 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | 0.10 | -0.07 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | -0.00 | -0.02 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,469 | 1,430 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,490 | 1,430 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,467 | 1,398 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,525 | 1,434 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,491 | 1,421 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,480 | 1,426 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,474 | 1,404 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 74.3 | 46.9 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 41.8 | 14.2 |
| Artificial Analysisreported | GPQA Diamond% of questions | 92.0% | 74.8% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 48.7% | 13.8% |
| Artificial Analysisreported | IFBench% of instructions | 62.2% | 68.8% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 77.7% | 69.3% |
| Artificial Analysisreported | SciCode% of problems | 54.4% | 40.2% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 84.6% | 50.6% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 21.7% | 0.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 58.3% | 33.3% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 34.2% | 15.1% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 94.4% | 94.2% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 6.0% | 18.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.40 | 0.35 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 65.9 | 45.5 |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.