Performance Benchmarks for gemini-4-argon-high

Analyze how gemini-4-argon-high stacks up against other frontier models in terms of cost-to-performance and raw intelligence (LMArena Elo).

2026 Performance Summary

🚀 Intelligence (Elo): 1525
💰 API Cost (Input): $0.000002 / 1M tokens
⚡ API Cost (Output): $0.00001 / 1M tokens
⏱️ Real-world Throughput: 29 tokens/s

Analysis: While gemini-4-argon-high is a capable model, it is currently outperformed in efficiency by hy4-preview. hy4-preview sits higher on the Pareto line, offering approximately 107 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	60
claude-haiku-5.5-high	1585	$1e-7	178
glm-5.3-max	1479	$7.9e-8	75
glm-5.2-max	1475	$5e-8	111
deepseek-v4.1-flash-max	1475	$1.3e-9	118

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