free-solar-evo-v0.11: benchmark results
Freewheelin AI's free-solar-evo v0.11, built on their free-solar-evo-model base using a method inspired by a Sakana AI project. Provider: Freewheelin. Released 2024-04-24. Access: Open.
Aggregate Rating 1424 ± 20, rank #1128 of 1656 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 83.85 | Normalized accuracy (%) | 99.6 |
| Open Korean LLM - KorNAT-Helpful | 75.38 | Normalized accuracy (%) | 99.5 |
| Open Chinese LLM - TruthfulQA MC | 69.02 | Accuracy (%) | 99.1 |
| Open LLM Leaderboard - MuSR | 50.52 | Score | 98.8 |
| Open Korean LLM - Ko-Winogrande | 72.85 | Accuracy (%) | 98.3 |
| Open Korean LLM - KorNAT-CKA | 38.47 | Normalized accuracy (%) | 97.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 27.78 | Normalized accuracy (%) | 95 |
| Open Chinese LLM - HellaSwag | 69.01 | Accuracy (%) | 89.9 |
| Open Korean LLM Leaderboard | 40.64 | Average Score (%) | 78 |
| Open Ko-LLM Leaderboard | 40.64 | Average (%) | 77.9 |
| Open Chinese LLM - WinoGrande | 66.22 | Accuracy (%) | 77.1 |
| Open Chinese LLM - ARC Challenge | 55.89 | Accuracy (%) | 70.4 |
Interactive version: theaggregate.ai/model?slug=free-solar-evo-v0-11 · How It Works · Data refreshed daily, snapshot 2026-10-20.