yi-34B-200k-rawrr-dpo-2: benchmark results
Provider: 01.AI. Access: Open.
Aggregate Rating 1478 ± 37, rank #2684 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 75.96 | Accuracy (%) (5-shot) | 97.1 |
| Open LLM Leaderboard v1 - WinoGrande | 83.19 | Accuracy (%) (5-shot) | 87.5 |
| Open LLM Leaderboard v1 - GSM8K | 61.79 | Accuracy (%) (5-shot) | 74.6 |
| Open LLM Leaderboard v1 - HellaSwag | 84.74 | Normalized accuracy (%) (10-shot) | 68.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 64.68 | Normalized accuracy (%) (25-shot) | 67.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.15 | MC2 (%) (0-shot) | 33.6 |
Interactive version: theaggregate.ai/model?slug=yi-34b-200k-rawrr-dpo-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.