BenchLeader
China MobileAuto-detected

JT-4.1 Flash 236B A21B

Not yet ranked: too few independent results so far.

Blended price
Output speed
First answer
Context
256k
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Knowledge60
  2. Multimodal48
  3. Long context62
  4. Composite63

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
GPQA Diamond (AA)not in index84.5%#136Artificial Analysis
Humanity's Last Exam (AA)not in index17.8%#175Artificial Analysis

Knowledge

BenchmarkdefaultSource
AA-Omniscience-8.8#131Artificial Analysis

Multimodal

BenchmarkdefaultSource
MMMU-Pro64.1%#153Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR71.3%#149Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index27.3#98Artificial Analysis

See also

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