GritLM-8x7B-KTO: benchmark results
Contextual AI's KTO-tuned GritLM 8x7B, a Mixtral-based GRIT model that unifies text generation and embedding in one checkpoint. Provider: GritLM. Released 2024-04-17. Access: Open.
Aggregate Rating 1485 ± 40, rank #2600 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - BBH | 58.2 | Score | 79.3 |
| Open Chinese LLM - WinoGrande | 65.59 | Accuracy (%) | 73.4 |
| Open LLM Leaderboard - IFEval | 57.14 | Score | 69 |
| Open Chinese LLM Leaderboard | 60.06 | Official Nonzero-Task Mean (%) | 67.8 |
| Open Chinese LLM - ARC Challenge | 54.35 | Accuracy (%) | 65.4 |
| Open LLM Leaderboard - MuSR | 42.17 | Score | 62.4 |
| Open Chinese LLM - HellaSwag | 61.31 | Accuracy (%) | 61.8 |
| Open Chinese LLM - C-Eval Semantic | 72.97 | Accuracy (%) | 60.7 |
| Open Chinese LLM - CMMLU | 56.28 | Accuracy (%) | 60.7 |
| Open LLM Leaderboard - MMLU-Pro | 36.48 | Score | 56.8 |
| Open LLM Leaderboard - MATH Level 5 | 12.24 | Score | 54.9 |
| Open LLM Leaderboard - GPQA | 29.61 | Score | 51.6 |
Interactive version: theaggregate.ai/model?slug=gritlm-8x7b-kto · How It Works · Data refreshed daily, snapshot 2026-11-08.