BenchAtlas

Rankings / xAI

Grok 2 1212

released 2024-12-12

BenchAtlas Index

as of 2026-07-14
30.5
base configuration
rank #352
6 families · 3 categories · medium

Benchmark evidence

12 results
external indices
ECI130.8 pointsindependentEpoch AI Benchmarking Hub
knowledge science
GPQA Diamond53.8 %independentEpoch AI Benchmarking Hub
2025-01-27
GPQA Diamond
implementation=vals-ai
50.8 %independentVals AI
MMLU-Pro
implementation=vals-ai
75.5 %independentVals AI
professional
CorpFin51.1 %independentVals AI
MedQA92.3 %independentVals AI
TaxEval67.0 %independentVals AI
reasoning math
AIME
implementation=vals-ai
15.2 %independentVals AI
FrontierMath0.7 %independentEpoch AI Benchmarking Hub
2025-03-06
MATH-500
implementation=vals-ai
78.4 %independentVals AI
MATH Level 563.5 %independentEpoch AI Benchmarking Hub
2025-02-17
OTIS Mock AIME 2024–202511.5 %independentEpoch AI Benchmarking Hub
2025-02-25

Related variants