RedPajama-INCITE-7B-Base: benchmark results
Provider: Together. Released 2023-05-05. Access: Open.
Unified ELO 1302 ± 1, rank #1344 of 1392 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenBookQA | 40 | Accuracy (%) | 28.6 |
| HellaSwag | 70.3 | Accuracy (%) | 26.3 |
| BoolQ | 69.3 | Accuracy (%) | 24.7 |
| PIQA | 76.9 | Accuracy (%) | 23.3 |
| ARC Challenge (AI2) | 39.1 | Accuracy (%) | 19.7 |
| WinoGrande | 63.8 | Accuracy (%) | 17.5 |
| Open LLM Leaderboard - MuSR | 3.02 | Score | 14.1 |
| Open LLM Leaderboard - IFEval | 20.82 | Score | 13.2 |
| Open LLM Leaderboard - MATH Level 5 | 1.59 | Score | 11.6 |
| Open LLM Leaderboard - BBH | 5.09 | Score | 10.3 |
| Open LLM Leaderboard - MMLU-Pro | 2.19 | Score | 9.5 |
| Open LLM Leaderboard - GPQA | 0.67 | Score | 8 |
Interactive version: theaggregate.ai/model?slug=redpajama-incite-7b-base · How It Works · Data refreshed daily, snapshot 2026-09-05.