Performance Benchmarks for gemini-3.6-flash

Analyze how gemini-3.6-flash stacks up against other frontier models in terms of cost-to-performance and raw intelligence (LMArena Elo).

2026 Performance Summary

🚀 Intelligence (Elo): 1485
💰 API Cost (Input): $0.0000015 / 1M tokens
⚡ API Cost (Output): $0.0000075 / 1M tokens
⏱️ Real-world Throughput: 164 tokens/s

Analysis: While gemini-3.6-flash is a capable model, it is currently outperformed in efficiency by hy3. hy3 sits higher on the Pareto line, offering approximately 42 points more intelligence (Elo) for a comparable or lower API cost.

Highly Recommended Alternatives

Frontier Model	LMArena Elo	API Cost (1M)	Throughput
hy3	1527	$1.4e-7	60
gemma-4-31b	1451	$1.2e-7	77
deepseek-v4-flash-thinking	1439	$9.38e-8	82
gemma-4-26b-a4b	1438	$7e-8	71
qwen3.5-flash	1397	$6.5e-8	82

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