Performance Benchmarks for gpt-5.5

Analyze how gpt-5.5 stacks up against other frontier models in terms of cost-to-performance and raw intelligence (LMArena Elo).

2026 Performance Summary

🚀 Intelligence (Elo): 1474
💰 API Cost (Input): $0.00000125 / 1M tokens
⚡ API Cost (Output): $0.00001 / 1M tokens
⏱️ Real-world Throughput: 57.5 tokens/s

Analysis: While gpt-5.5 is a capable model, it is currently outperformed in efficiency by gemini-3.5-flash. gemini-3.5-flash sits higher on the Pareto line, offering approximately 3 points more intelligence (Elo) for a comparable or lower API cost.

Highly Recommended Alternatives

Frontier Model	LMArena Elo	API Cost (1M)	Throughput
gemini-3.5-flash	1477	$0.0000015	63
glm-5.1	1475	$9.8e-7	25
gemini-3-flash	1473	$5e-7	61
mimo-v2.5-pro	1465	$4.35e-7	35
gemma-4-31b	1451	$1.2e-7	42

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