smolphin-test-stack: benchmark results
Provider: Other.
Aggregate Rating 1141 ± 35, rank #10102 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 62.04 | Accuracy (%) (5-shot) | 15.1 |
| Open LLM Leaderboard v1 - HellaSwag | 59.94 | Normalized accuracy (%) (10-shot) | 14.1 |
| Open LLM Leaderboard v1 - GSM8K | 0.76 | Accuracy (%) (5-shot) | 14 |
| Open LLM Leaderboard v1 - ARC Challenge | 32.68 | Normalized accuracy (%) (25-shot) | 11 |
| Open LLM Leaderboard v1 - MMLU | 25.16 | Accuracy (%) (5-shot) | 6.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 36.64 | MC2 (%) (0-shot) | 4.1 |
Interactive version: theaggregate.ai/model?slug=smolphin-test-stack · How It Works · Data refreshed daily, snapshot 2026-11-08.