testmerge-7B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1503 ± 21, rank #1179 of 2928 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 89.37 | Normalized accuracy (%) (10-shot) | 99.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 74.15 | Normalized accuracy (%) (25-shot) | 99 |
| Open LLM Leaderboard v1 - WinoGrande | 85.32 | Accuracy (%) (5-shot) | 98.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 74.67 | MC2 (%) (0-shot) | 95.1 |
| Open LLM Leaderboard - MuSR | 46.86 | Score | 90.8 |
| Open LLM Leaderboard v1 - GSM8K | 64.59 | Accuracy (%) (5-shot) | 78.6 |
| Open LLM Leaderboard v1 - MMLU | 64.07 | Accuracy (%) (5-shot) | 65.4 |
| Open LLM Leaderboard - BBH | 51.9 | Score | 58.3 |
| Open LLM Leaderboard - GPQA | 30.03 | Score | 56.5 |
| Open LLM Leaderboard - IFEval | 39.8 | Score | 39.7 |
| Open LLM Leaderboard - MMLU-Pro | 30.6 | Score | 38.6 |
| Open LLM Leaderboard - MATH Level 5 | 6.87 | Score | 36.9 |
Interactive version: theaggregate.ai/model?slug=testmerge-7b · How It Works · Data refreshed daily, snapshot 2026-09-23.