DeepSeek V4 Pro 0813 (Non-reasoning) vs MiMo-V2.5
Which is better for the money: DeepSeek V4 Pro 0813 (Non-reasoning) by DeepSeek or MiMo-V2.5 by Xiaomi? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick MiMo-V2.5
MiMo-V2.5 vs DeepSeek V4 Pro 0813 (Non-reasoning): 6.9% more intelligence, 86.3% less cost to run the AA benchmark, and 700.0% slower end-to-end.
| Metric | DeepSeek V4 Pro 0813 (Non-reasoning) | MiMo-V2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 20.4 | 21.8 | +6.9% MiMo-V2.5 is 6.9% more intelligent |
| Total AA cost (lower is better) | $450.76 | $61.93 | −86.3% MiMo-V2.5 is 86.3% cheaper |
| End-to-end time (lower is better) | 6.74s | 53.92s | +700.0% MiMo-V2.5 is 700.0% slower |
| Price per 1M tokens (in / out) | $1.32 / $3.96 | $0.13 / $0.27 | |
| Input modalities | Text | Text, Image |
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Pro 0813 (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- MiMo-V2.5 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 34.50 for $56.4.
DeepSeek V4 Pro 0813 (Non-reasoning)MiMo-V2.5Today's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/deepseek-v4-pro-non-reasoning/mimo-v2-5-0424 · Markdown: /api/v1/compare/deepseek-v4-pro-non-reasoning/mimo-v2-5-0424?format=md · llms.txt · agent skill