Arcee-Blitz — benchmark results
Arcee AI's 24B Mistral Small 3-based workhorse model, distilled from DeepSeek-V3. Provider: Arcee AI. Released 2025-02-07. Access: Open.
Unified ELO 1564 ± 30, rank #581 of 1776 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MMLU-Pro | 57.26 | Score | 99.9 |
| Open LLM Leaderboard - MuSR | 23.82 | Score | 98.6 |
| Open LLM Leaderboard - GPQA | 18.01 | Score | 96.2 |
| Open LLM Leaderboard - BBH | 50.73 | Score | 93.4 |
| Open LLM Leaderboard - MATH Level 5 | 34.82 | Score | 85.2 |
| Open LLM Leaderboard - IFEval | 55.43 | Score | 67 |
| UGI - Willingness (W/10) | 6.8 | W/10 Score | 66.6 |
| UGI - Natural Intelligence | 23.14 | NatInt Score | 55.5 |
| UGI Leaderboard | 32.57 | UGI Score | 41.6 |
| UGI - Writing | 23.26 | Writing Score | 18.9 |
Interactive version: theaggregate.ai/model?slug=arcee-blitz · How the rankings work · Data refreshed daily, snapshot 2026-07-22.