free-solar-evo-v0.13: benchmark results
Freewheelin AI's free-solar-evo v0.13, built on their free-solar-evo-model base using a method inspired by a Sakana AI project. Provider: Freewheelin. Released 2024-04-28. Access: Open.
Aggregate Rating 1434 ± 20, rank #1080 of 1656 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Chinese LLM - TruthfulQA MC | 69.58 | Accuracy (%) | 99.7 |
| Open Korean LLM - KorNAT-Harmless | 85.08 | Normalized accuracy (%) | 99.7 |
| Open Korean LLM - KorNAT-Helpful | 76.8 | Normalized accuracy (%) | 99.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 29.29 | Normalized accuracy (%) | 99.2 |
| Open Korean LLM - KorNAT-CKA | 39.81 | Normalized accuracy (%) | 99 |
| Open Korean LLM - Ko-Winogrande | 73.56 | Accuracy (%) | 98.8 |
| Open LLM Leaderboard - MuSR | 50.52 | Score | 98.8 |
| Open Chinese LLM - HellaSwag | 68.4 | Accuracy (%) | 87.4 |
| Open Korean LLM Leaderboard | 41.51 | Average Score (%) | 83 |
| Open Ko-LLM Leaderboard | 41.51 | Average (%) | 82.9 |
| Open Chinese LLM - WinoGrande | 66.22 | Accuracy (%) | 77.1 |
| Open Chinese LLM - ARC Challenge | 55.72 | Accuracy (%) | 69.5 |
Interactive version: theaggregate.ai/model?slug=free-solar-evo-v0-13 · How It Works · Data refreshed daily, snapshot 2026-10-20.