GritLM-7B-KTO: benchmark results
Provider: Other. Released 2024-04-16. Access: Open.
Unified ELO 1393 ± 1, rank #1168 of 1392 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 53.1 | Score | 63.1 |
| Open Chinese LLM - TruthfulQA MC | 54.48 | Accuracy (%) | 57.3 |
| Open Korean LLM Leaderboard | 36.52 | Average Score (%) | 54.6 |
| Open LLM Leaderboard - GPQA | 6.38 | Score | 53.5 |
| Open LLM Leaderboard - BBH | 27.9 | Score | 44.9 |
| Open LLM Leaderboard - MuSR | 6.64 | Score | 31.5 |
| Open LLM Leaderboard - MMLU-Pro | 18.67 | Score | 28.4 |
| Open Chinese LLM - ARC Challenge | 46.84 | Accuracy (%) | 25.2 |
| Open LLM Leaderboard - MATH Level 5 | 2.72 | Score | 17.5 |
| Open Chinese LLM - WinoGrande | 60.46 | Accuracy (%) | 17.2 |
| Open Chinese LLM - GSM8K | 23.65 | Accuracy (%) | 16.9 |
| Open Chinese LLM - C-Eval Semantic | 53.66 | Accuracy (%) | 14.2 |
Interactive version: theaggregate.ai/model?slug=gritlm-7b-kto · How It Works · Data refreshed daily, snapshot 2026-09-05.