BenchLeader
LongCatOpen weightsAuto-detected

LongCat Flash Lite

Best configuration ranks #431 of 610 on the BenchLeader Index at 43.9 ±4.4.

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. Overall index44
  2. Agents & tools43
  3. Knowledge31
  4. Instruction following45
  5. Long context39
  6. Composite43

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 index63.6%#335Artificial Analysis
Humanity's Last Exam (AA)not in index5.8%#340Artificial Analysis

Agents & tools

Knowledge

BenchmarkdefaultSource
AA-Omniscience-70.1#436Artificial Analysis

Instruction following

BenchmarkdefaultSource
IFBench43.1%#224Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR28.3%#326Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index11.5#285Artificial Analysis

See also

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