BenchLeader
MetaAuto-detected

Llama Llama 3.3 70B Turbo

Best configuration ranks #545 of 610 on the BenchLeader Index at 38.6 ±9.2. 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 index39
  2. Coding22
  3. Maths41
  4. Knowledge37

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 index50.0%#117Vals AI

Coding

BenchmarkdefaultSource
LiveCodeBench36.3%#128Vals AI

Maths

BenchmarkdefaultSource
AIME (Vals)16.0%#81Vals AI
MGSM91.1%#29Vals AI

Knowledge

BenchmarkdefaultSource
MMLU-Pro69.9%#114Vals AI
LegalBench77.2%#100Vals AI
TaxEval59.4%#126Vals AI

See also

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