Redemption_Wind_24B — benchmark results
SicariusSicariiStuff's lightly fine-tuned Mistral Small 24B in ChatML, released as a friendly base for further community fine-tuning. Provider: Other. Released 2025-02-06. Access: Open.
Unified ELO 1474 ± 57, rank #892 of 1776 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MMLU-Pro | 49.25 | Score | 98 |
| Open LLM Leaderboard - GPQA | 17.79 | Score | 95.7 |
| Open LLM Leaderboard - BBH | 48.42 | Score | 88.5 |
| Open LLM Leaderboard - MATH Level 5 | 18.58 | Score | 68.4 |
| Open LLM Leaderboard - MuSR | 11.18 | Score | 57.9 |
| UGI - Willingness (W/10) | 4.8 | W/10 Score | 36.1 |
| UGI Leaderboard | 27.73 | UGI Score | 24.8 |
| UGI - Natural Intelligence | 15.79 | NatInt Score | 22.9 |
| Open LLM Leaderboard - IFEval | 25.01 | Score | 20.5 |
Interactive version: theaggregate.ai/model?slug=redemption-wind-24b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.