BenchLeader
AlibabaAuto-detected

Qwen-14B

Not yet ranked: too few independent results so far. Released 24 Sept 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. Reasoning27
  2. Coding30
  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 Prompts1141#320LMArena

Coding

BenchmarkdefaultSource
LMArena Coding1197#302LMArena

Human preference

BenchmarkdefaultSource
LMArena Text1139#320LMArena

Composite

BenchmarkdefaultSource
Epoch Capabilities Indexnot in index112.9#184Epoch AI Benchmarking Hub

See also

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