Sirius-10B: benchmark results
A passthrough merge by FelixChao, with the exact parent checkpoints and merge recipe recorded in its release card. Provider: FelixChao. Access: Open.
Aggregate Rating 1454 ± 39, rank #3585 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - ARC Challenge | 71.93 | Normalized accuracy (%) (25-shot) | 90.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 68.1 | MC2 (%) (0-shot) | 87 |
| Open LLM Leaderboard v1 - WinoGrande | 82.79 | Accuracy (%) (5-shot) | 85.6 |
| Open LLM Leaderboard v1 - HellaSwag | 87.32 | Normalized accuracy (%) (10-shot) | 85.5 |
| Open LLM Leaderboard v1 - MMLU | 64.73 | Accuracy (%) (5-shot) | 75.6 |
| Open LLM Leaderboard v1 - GSM8K | 62.09 | Accuracy (%) (5-shot) | 75.1 |
Interactive version: theaggregate.ai/model?slug=sirius-10b · How It Works · Data refreshed daily, snapshot 2026-11-08.