Grok 3 Mini Fast High Reasoning

release date unknown

BenchAtlas Index

as of 2026-07-14

Not enough benchmark coverage for a composite score (needs ≥4 families across ≥3 categories). The per-benchmark evidence below stands on its own — sparse coverage is an evidence gap, not a low score.

Benchmark evidence

8 results

knowledge science

GPQA Diamond implementation=vals-ai	high effort	79.3 %	independent	Vals AI
MMLU-Pro implementation=vals-ai	high effort	81.4 %	independent	Vals AI

professional

CorpFin	high effort	61.1 %	independent	Vals AI
LegalBench	high effort	83.1 %	independent	Vals AI
MedQA	high effort	90.1 %	independent	Vals AI
TaxEval	high effort	71.1 %	independent	Vals AI

reasoning math

AIME implementation=vals-ai	high effort	85.0 %	independent	Vals AI
MATH-500 implementation=vals-ai	high effort	94.2 %	independent	Vals AI