Performance Benchmarks for mercury-2

Analyze how mercury-2 stacks up against other frontier models in terms of cost-to-performance and raw intelligence (LMArena Elo).

2026 Performance Summary

🚀 Intelligence (Elo): 1348
💰 API Cost (Input): $2.5e-7 / 1M tokens
⚡ API Cost (Output): $7.5e-7 / 1M tokens
⏱️ Real-world Throughput: 297 tokens/s

Analysis: While mercury-2 is a capable model, it is currently outperformed in efficiency by mimo-v2.5-pro. mimo-v2.5-pro sits higher on the Pareto line, offering approximately 118 points more intelligence (Elo) for a comparable or lower API cost.

Highly Recommended Alternatives

Frontier Model	LMArena Elo	API Cost (1M)	Throughput
mimo-v2.5-pro	1466	$4.35e-7	65
qwen3.7-plus	1460	$3.2e-7	15
gemma-4-31b	1451	$2.2e-7	138
deepseek-v4-flash-thinking	1438	$9.8e-8	73
qwen3-235b-a22b-instruct-2507	1423	$9e-8	39

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