BenchLeader
MetaAuto-detected

Llama Llama 4 Scout 17B 16e

Best configuration ranks #590 of 610 on the BenchLeader Index at 35.8 ±6.2. Last measured 1 Sept 2026.

Blended price
Output speed
First answer
Context
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index36
  2. Coding24
  3. Maths38
  4. Knowledge30

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 (Vals)not in index47.0%#120Vals AI

Coding

BenchmarkdefaultSource
LiveCodeBench38.5%#126Vals AI

Maths

BenchmarkdefaultSource
AIME (Vals)19.0%#78Vals AI
MGSM88.0%#53Vals AI

Knowledge

BenchmarkdefaultSource
MMLU-Pro69.6%#115Vals AI
LegalBench72.0%#108Vals AI
CorpFin46.8%#106Vals AI
TaxEval55.2%#132Vals AI
MedQA50.9%#87Vals AI

See also

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