01.AIAuto-detected
Yi-34B
Best configuration ranks #592 of 610 on the BenchLeader Index at 35.8 ±5.9. Last measured 2 Sept 2026. Released 2 Nov 2023.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Overall index36
- Reasoning20
- Coding31
- Maths26
- Human preference32
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond | 14.7%#269 | Epoch AI Benchmarking Hub |
| LMArena Hard Prompts | 1183#299 | LMArena |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1205#300 | LMArena |
Maths
| Benchmark | default | Source |
|---|---|---|
| MATH Level 5 | 5.2%#87 | Epoch AI Benchmarking Hub |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1183#293 | LMArena |
Composite
| Benchmark | default | Source |
|---|---|---|
| Epoch Capabilities Indexnot in index | 117.3#173 | Epoch AI Benchmarking Hub |
See also
Data as of 9 Sept 2026. Compare with another model.