Trinity-2-Codestral-22B-v0.2: benchmark results
migtissera's v0.2 fine-tune of Mistral's Codestral-22B in his Trinity series of coding-focused models. Provider: Arcee AI. Released 2024-08-13. Access: Open.
Unified ELO 1502 ± 1, rank #752 of 1553 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM Leaderboard | 44.2 | Average Score (%) | 88.4 |
| Open LLM Leaderboard - BBH | 37.79 | Score | 77.6 |
| Open LLM Leaderboard - GPQA | 7.72 | Score | 65.2 |
| Open LLM Leaderboard - IFEval | 44.3 | Score | 48.1 |
| Open LLM Leaderboard - MMLU-Pro | 26.15 | Score | 47.7 |
| Open LLM Leaderboard - MuSR | 9.06 | Score | 43.8 |
| Open LLM Leaderboard - MATH Level 5 | 8.69 | Score | 43.2 |
Interactive version: theaggregate.ai/model?slug=trinity-2-codestral-22b-v0-2 · How It Works · Data refreshed daily, snapshot 2026-09-08.