evals.report
BenchmarksLabsCompareRun guidesIn the wild
MetaLlama

Llama 4 Scout

Meta · Llama. Released Apr 5, 2025.

Llama 4 Scout is a model from Meta in the Llama family, released Apr 5, 2025. evals.report tracks 18 reported Llama 4 Scout benchmark scores across GPQA Diamond, FrontierMath, AIME (OTIS Mock), Artificial Analysis Intelligence Index, Epoch Capabilities Index, MMLU-Pro, MathVista, GDPval, and 10 more — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.

Open18 results

Benchmark results 18

Compare this model
BenchmarkCategoryScoreMetricStatusDate
GPQA DiamondReasoning51.8%accuracyOfficialApr 5, 2025Details
FrontierMathReasoning0.0%accuracyOfficialApr 5, 2025Details
AIME (OTIS Mock)Reasoning7.8%accuracyOfficialApr 5, 2025Details
Artificial Analysis Intelligence IndexReasoning13.5IndexUnverifiedApr 5, 2025Details
Epoch Capabilities IndexReasoning130.6IndexOfficialApr 5, 2025Details
MMLU-ProReasoning75.2%accuracyVerifiedApr 5, 2025Details
MathVistaMultimodal70.7%accuracyVerifiedApr 5, 2025Details
GDPvalAgents270EloOfficialApr 5, 2025Details
LiveCodeBenchCoding29.9%Pass@1UnverifiedApr 5, 2025Details
SciCodeCoding17.0%accuracyUnverifiedApr 5, 2025Details
MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark)Multimodal69.4%accuracyUnverifiedApr 5, 2025Details
Global-MMLUReasoning74.1%accuracyUnverifiedApr 5, 2025Details
EQ-Bench Creative Writing v3Chat preference883EloVerifiedApr 5, 2025Details
Design ArenaChat preference844EloVerifiedApr 5, 2025Details
BigCodeBenchCoding16.9%calibrated Pass@1VerifiedApr 5, 2025Details
ZeroBenchMultimodal0.0% (pass@1)accuracyVerifiedApr 5, 2025Details
Vectara Hallucination LeaderboardOther7.7%Hallucination RateOfficialApr 5, 2025Details
PolyMath: Evaluating Mathematical Reasoning in Multilingual ContextsReasoning20.9Difficulty-Weighted Accuracy (DW-ACC)VerifiedApr 5, 2025Details