Performance Benchmarks for qwen3-235b-a22b-thinking-2507

Analyze how qwen3-235b-a22b-thinking-2507 stacks up against other frontier models in terms of cost-to-performance and raw intelligence (LMArena Elo).

2026 Performance Summary

🚀 Intelligence (Elo): 1400
💰 API Cost (Input): $2.3e-7 / 1M tokens
⚡ API Cost (Output): $0.0000023 / 1M tokens
⏱️ Real-world Throughput: 60 tokens/s

Analysis: While qwen3-235b-a22b-thinking-2507 is a capable model, it is currently outperformed in efficiency by hy4-preview. hy4-preview sits higher on the Pareto line, offering approximately 232 points more intelligence (Elo) for a comparable or lower API cost.

Highly Recommended Alternatives

Frontier Model	LMArena Elo	API Cost (1M)	Throughput
hy4-preview	1632	$8.34e-7	23
gemini-3.8-flash-high	1495	$7.5e-7	92
kimi-k3-max	1488	$6.2e-7	60
mimo-v2.6-pro	1480	$4.35e-7	31
glm-5.3-max	1478	$4.9e-8	90

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