Fimbulvetr-11B-v2 — benchmark results
Sao10K's Solar 10.7B-based 11B fine-tune, a popular roleplay model supporting Alpaca and Vicuna prompt formats. Provider: Other. Released 2024-02-06. Access: Open.
Unified ELO 1468 ± 23, rank #920 of 1776 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 14.92 | Score | 80.6 |
| UGI - Willingness (W/10) | 6.5 | W/10 Score | 62.1 |
| Open LLM Leaderboard - IFEval | 51 | Score | 60.9 |
| Open LLM Leaderboard - GPQA | 5.59 | Score | 46.9 |
| Open LLM Leaderboard - MMLU-Pro | 25.57 | Score | 46.2 |
| Open LLM Leaderboard - MATH Level 5 | 6.8 | Score | 36.7 |
| Open LLM Leaderboard - BBH | 22.66 | Score | 34 |
| UGI Leaderboard | 30.01 | UGI Score | 31.4 |
| UGI - Natural Intelligence | 16.32 | NatInt Score | 25.4 |
| UGI - Writing | 24.27 | Writing Score | 20.7 |
Interactive version: theaggregate.ai/model?slug=fimbulvetr-11b-v2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.