SOLAR-math-2x10.7B: benchmark results
An experimental merge released by macadeliccc of two SOLAR models, intended to improve mathematics while retaining other skills. Provider: macadeliccc. Access: Open.
Aggregate Rating 1457 ± 35, rank #3479 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 71.04 | Accuracy (%) (5-shot) | 95 |
| Open LLM Leaderboard v1 - MMLU | 66.9 | Accuracy (%) (5-shot) | 88.5 |
| Open LLM Leaderboard v1 - WinoGrande | 83.35 | Accuracy (%) (5-shot) | 88.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 64.21 | MC2 (%) (0-shot) | 81.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 68.43 | Normalized accuracy (%) (25-shot) | 80.4 |
| Open LLM Leaderboard v1 - HellaSwag | 86.31 | Normalized accuracy (%) (10-shot) | 80.1 |
Interactive version: theaggregate.ai/model?slug=solar-math-2x10-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.