BenchLeader
TencentAuto-detected

Hunyuan Hy3

Not yet ranked: too few independent results so far.

Blended price
Output speed
First answer
Context
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Reasoning61
  2. Coding47
  3. Human preference60

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

BenchmarkdefaultSourceTrend
LMArena Hard Prompts1439#109LMArena

Coding

BenchmarkdefaultSourceTrend
LMArena Coding1461#112LMArena
LMArena WebDev1356#90LMArena

Human preference

BenchmarkdefaultSourceTrend
LMArena Text1413#118LMArena

See also

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