Yi-34B-200K: benchmark results
01.AI's 34B bilingual base model trained on 3T tokens (November 2023), with its context window extended to 200K. Provider: 01.AI. Released 2023-11-05. Access: Open.
Aggregate Rating 1413 ± 19, rank #1176 of 1656 rated models, from 61 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 75.56 | Accuracy (%) (5-shot) | 97 |
| Open LLM Leaderboard - GPQA | 35.65 | Score | 89.9 |
| Open Chinese LLM - WinoGrande | 69.14 | Accuracy (%) | 89.3 |
| Open Portuguese LLM - OAB Exams | 55.17 | Accuracy (%) | 87.8 |
| Open LLM Leaderboard v1 - WinoGrande | 82.87 | Accuracy (%) (5-shot) | 86 |
| Open Portuguese LLM - BLUEX | 64.81 | Accuracy (%) | 85.7 |
| Open LLM Leaderboard - MMLU-Pro | 45.35 | Score | 84.3 |
| Open Portuguese LLM - ENEM | 71.73 | Accuracy (%) | 81.3 |
| Open Chinese LLM - CMMLU | 68.37 | Accuracy (%) | 80.8 |
| Open Chinese LLM - HellaSwag | 66.01 | Accuracy (%) | 80.5 |
| Open Chinese LLM - C-Eval Semantic | 85.72 | Accuracy (%) | 77.8 |
| Open Chinese LLM - ARC Challenge | 57.17 | Accuracy (%) | 74.3 |
Interactive version: theaggregate.ai/model?slug=yi-34b-200k · How It Works · Data refreshed daily, snapshot 2026-10-20.