BenchLeader
MosaicMLAuto-detected

MPT-30B

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. Reasoning29
  2. Coding27
  3. Human preference28

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 Prompts1157#310LMArena

Coding

BenchmarkdefaultSource
LMArena Coding1168#315LMArena

Human preference

BenchmarkdefaultSource
LMArena Text1150#312LMArena

Composite

BenchmarkdefaultSource
Epoch Capabilities Indexnot in index100.3#210Epoch AI Benchmarking Hub

See also

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