Benchmarks for gemma-4-31b

Analyze how gemma-4-31b stacks up against other models in terms of cost-to-performance and raw intelligence (LMArena Elo).

Performance Summary

🚀 Intelligence (Elo): 1452
💰 Price (Input): $1.4e-7 / 1M tokens
⚡ Price (Output): $4e-7 / 1M tokens
⏱️ Throughput: 9 tokens/s

Recommended Alternatives

Frontier Model	LMArena Elo	API Cost (1M)	Throughput
kimi-k2.5-thinking	1453	$3.827e-7	16
qwen3-235b-a22b-instruct-2507	1422	$7.1e-8	9
qwen3.5-flash	1402	$6.5e-8	115
glm-4.7-flash	1369	$6e-8	86
gpt-oss-120b	1354	$3.9e-8	50

*These models represent the Pareto Frontier (optimal cost-to-performance).*