Performance Benchmarks for beam-1.0-501b-a23b

Analyze how beam-1.0-501b-a23b stacks up against other frontier models in terms of cost-to-performance and raw intelligence (LMArena Elo).

2026 Performance Summary

🚀 Intelligence (Elo): 1438
💰 API Cost (Input): $0.000001 / 1M tokens
⚡ API Cost (Output): $0.000003 / 1M tokens
⏱️ Real-world Throughput: 63 tokens/s

Analysis: While beam-1.0-501b-a23b is a capable model, it is currently outperformed in efficiency by Hy4 preview. Hy4 preview sits higher on the Pareto line, offering approximately 194 points more intelligence (Elo) for a comparable or lower API cost.

Highly Recommended Alternatives

Frontier Model	LMArena Elo	API Cost (1M)	Throughput
Hy4 preview	1631	$8.34e-7	36
Claude Haiku 5.5 (High)	1585	$1e-7	183
glm-5.3-max	1479	$7.9e-8	134
glm-5.3-flash	1474	$4.64e-8	121
gpt-oss-20b	1317	$1.8e-8	12

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