BenchLeader
LMSYSAuto-detected

vicuna-13b-v1.1

Not yet ranked: too few independent results so far. Released 12 Apr 2023.

Blended price
Output speed
First answer
Context
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Reasoning26
  2. Coding26
  3. Human preference27

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

BenchmarkdefaultSource
LMArena Hard Prompts1131#324LMArena

Coding

BenchmarkdefaultSource
LMArena Coding1163#318LMArena

Human preference

BenchmarkdefaultSource
LMArena Text1141#318LMArena

Composite

BenchmarkdefaultSource
Epoch Capabilities Indexnot in index94.3#219Epoch AI Benchmarking Hub

See also

Data as of 9 Sept 2026. Compare with another model.