Mistral Small Creative: benchmark results
Provider: Mistral. Released 2025-12-16. Access: API.
Unified ELO 1538 ± 1, rank #499 of 1392 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Multivac Evaluation | 9.6 | Avg Peer Score (0-10) | 100 |
| SpeechMap Compliance | 90.8 | % Requests Completed | 91.7 |
| EQ-Bench Creative Writing v3 | 1247.5 | Elo | 49 |
| Creative Writing v3 | 1371.1 | Elo score (self-reported) | 46.4 |
| Story Theory Bench | 84.3 | Score (%) | 20.6 |
| CringeBench | 1.66 | Cringe Score (0-10, lower is better) | 15.2 |
| RP-Bench | 75.7 | Combined Score | 14.3 |
| RP-Bench - Elo | 1360 | Elo | 14.3 |
| RP-Bench - Flaw Hunter | 59.6 | Flaw Hunter Score | 14.3 |
| EQ-Bench Longform Writing | 32.6 | Writing Score (0-100) | 10.1 |
| AI Chess Leaderboard (Reasoning) | 457 | Elo | 8.2 |
| RP-Bench - Objective | 85.2 | Objective Score | 0 |
Interactive version: theaggregate.ai/model?slug=mistral-small-creative · How It Works · Data refreshed daily, snapshot 2026-09-05.