MS-Meadowlark-22B: benchmark results
Allura-org's roleplay and storywriting merge of Mistral Small Instruct 22B fine-tunes, including SpringDragon and Gutenberg-Doppel components. Provider: allura-org. Released 2024-10-18. Access: Open.
Aggregate Rating 1527 ± 46, rank #1984 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 66.97 | Score | 79.2 |
| Open LLM Leaderboard - GPQA | 32.55 | Score | 78.5 |
| Open LLM Leaderboard - MATH Level 5 | 18.35 | Score | 68.1 |
| Open LLM Leaderboard - MMLU-Pro | 38.23 | Score | 66.6 |
| UGI - Writing | 36.57 | Writing Score | 59 |
| Open LLM Leaderboard - BBH | 51.63 | Score | 57 |
| UGI Leaderboard | 35.73 | UGI Score | 52.8 |
| UGI - Natural Intelligence | 20.71 | NatInt Score | 43.4 |
| UGI - Willingness (W/10) | 4.8 | W/10 Score | 38 |
| Open LLM Leaderboard - MuSR | 38.43 | Score | 31.7 |
Interactive version: theaggregate.ai/model?slug=ms-meadowlark-22b · How It Works · Data refreshed daily, snapshot 2026-11-08.