Yi-6B-Infinity-Chat: benchmark results
Provider: 01.AI.
Aggregate Rating 1340 ± 34, rank #7959 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 64.05 | Accuracy (%) (5-shot) | 65.1 |
| Open LLM Leaderboard v1 - GSM8K | 36.01 | Accuracy (%) (5-shot) | 51.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 50.75 | MC2 (%) (0-shot) | 49.4 |
| Open Korean LLM - Ko-EQ-Bench | 3.17 | EQ-Bench score | 49.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.57 | Normalized accuracy (%) (25-shot) | 35.7 |
| Open LLM Leaderboard v1 - WinoGrande | 73.95 | Accuracy (%) (5-shot) | 34.2 |
| Open LLM Leaderboard v1 - HellaSwag | 77.66 | Normalized accuracy (%) (10-shot) | 31.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 6.52 | Exact match, flexible extract (%) | 28.1 |
| Open Korean LLM - KorNAT-Harmless | 61.38 | Normalized accuracy (%) | 27.6 |
| Open Korean LLM - Ko-IFEval | 21.61 | Strict accuracy, prompt/instruction mean (%) | 21.8 |
| Open Korean LLM - KorNAT-Helpful | 42.98 | Normalized accuracy (%) | 20.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
Interactive version: theaggregate.ai/model?slug=yi-6b-infinity-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.