OpenChat / BerkeleyAuto-detected
Openchat 3.5
Not yet ranked: too few independent results so far.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 8k
- Reasoning32
- Coding34
- Human preference32
- Composite36
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 |
|---|---|---|
| LMArena Hard Prompts | 1187#296 | LMArena |
| GPQA Diamond (AA)not in index | 23.0%#517 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 4.8%#396 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1230#292 | LMArena |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1182#295 | LMArena |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 5.3#500 | Artificial Analysis |
See also
Data as of 9 Sept 2026. Compare with another model.