Llama 4 Behemoth Instruct Benchmark Details

Llama 4 Behemoth Instruct currently shows benchmark results led by MMLU-Pro (54 / 175, score 82.20), MMMU (30 / 74, score 76.10), MATH-500 (26 / 46, score 95).

Benchmark Results

Llama 4 Behemoth Instruct

Benchmark Results

Knowledge Exams

1 evaluations

Benchmark / mode

Score

Rank/total

MMLU-Pro

Standard Mode

82.20

54 / 175

Scientific Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

73.70

162 / 253

Mathematics

1 evaluations

Benchmark / mode

Score

Rank/total

MATH-500

Standard Mode

26 / 46

Algorithmic Coding

1 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Standard Mode

49.40

96 / 125

Visual Understanding

1 evaluations

Benchmark / mode

Score

Rank/total

MMMU

unknown

76.10

30 / 74

Compare with other models