Performance Benchmarks for mistral-small-24b-instruct-2501

Analyze how mistral-small-24b-instruct-2501 stacks up against other frontier models in terms of cost-to-performance and raw intelligence (LMArena Elo).

2026 Performance Summary

🚀 Intelligence (Elo): 1274
💰 API Cost (Input): $5e-8 / 1M tokens
⚡ API Cost (Output): $8e-8 / 1M tokens
⏱️ Real-world Throughput: 39 tokens/s

Analysis: While mistral-small-24b-instruct-2501 is a capable model, it is currently outperformed in efficiency by hy4-preview. hy4-preview sits higher on the Pareto line, offering approximately 350 points more intelligence (Elo) for a comparable or lower API cost.

Highly Recommended Alternatives

Frontier Model	LMArena Elo	API Cost (1M)	Throughput
hy4-preview	1624	$8.34e-7	38
deepseek-v4.1-flash-max	1614	$1.5e-7	85
glm-5.3-flash	1475	$9e-8	12
hy3	1456	$8.25e-8	59
deepseek-v4-flash-high-preview	1438	$4.956e-8	33

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