Claude Opus 4.6 vs Gemma 4 31B — Who Actually Wins? Real Benchmark Data (2026)

head to head

Claude Opus 4.6 vs Gemma 4 31B

6 shared benchmarks

4

wins

0

ties

2

wins

100.0%

AIME

89.2%

91.3%

GPQA Diamond

84.3%

53.1%

Humanity's Last Exam

19.5%

76.0%

LiveCodeBench

80.0%

82.0%

MMLU Pro

85.2%

93.0%

MRCR v2

66.4%