Yi 34B Chat — Benchmarks
Benchmark scores for Yi 34B Chat aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Knowledge
| Benchmark | Score | Rank |
|---|---|---|
| MMLU | 73.5% | #20 / 74 |
Math
| Benchmark | Score | Rank |
|---|---|---|
| GSM8K | 76.0% | #14 / 58 |
| MATH Level 5 | 5.1% | #29 / 31 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| BIG-Bench Hard | 71.7% | #6 / 36 |
| GPQA Diamond | 14.7% | #41 / 41 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.