gpt-oss-20b (High) vs MiMo-V2.5
Which is better for the money: gpt-oss-20b (High) by OpenAI or MiMo-V2.5 by Xiaomi? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
MiMo-V2.5 scores 12.8 points higher (21.8 vs 9.0) but costs 2.1× as much to run the benchmark ($61.9 vs $28.8; mid-range vs budget cost classes). Pick MiMo-V2.5 when the extra intelligence is worth the premium, otherwise gpt-oss-20b (High).
| Metric | gpt-oss-20b (High) | MiMo-V2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 9.0 | 21.8 | +142.2% MiMo-V2.5 is 2.4× more intelligent |
| Total AA cost (lower is better) | $28.81 | $61.93 | +115.0% MiMo-V2.5 is 2.1× more expensive |
| End-to-end time (lower is better) | 15.23s | 53.92s | +254.0% MiMo-V2.5 is 254.0% slower |
| Price per 1M tokens (in / out) | $0.05 / $0.22 | $0.13 / $0.27 | |
| Input modalities | Text | Text, Image |
MiMo-V2.5 vs gpt-oss-20b (High): 142.2% more intelligence, 115.0% more cost to run the AA benchmark, and 254.0% slower end-to-end.
Today's Pareto frontier
Against the frontier
- gpt-oss-20b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- MiMo-V2.5 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 34.50 for $56.4.
gpt-oss-20b (High)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/gpt-oss-20b/mimo-v2-5-0424 · Markdown: /api/v1/compare/gpt-oss-20b/mimo-v2-5-0424?format=md · llms.txt · agent skill