BenchAtlas

Rankings / Meta AI

Llama 4 Maverick 17B 128e Instruct Fp8

released 2025-04-05

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

5 results
external indices
ECI133.0 pointsindependentEpoch AI Benchmarking Hub
knowledge science
GPQA Diamond67.0 %independentEpoch AI Benchmarking Hub
2025-04-08
reasoning math
FrontierMath0.7 %independentEpoch AI Benchmarking Hub
2025-04-08
MATH Level 573.0 %independentEpoch AI Benchmarking Hub
2025-04-08
OTIS Mock AIME 2024–202520.6 %independentEpoch AI Benchmarking Hub
2025-04-08