Claude Haiku 5.5 (Max) vs Mistral Small 3.2
Which is better for the money: Claude Haiku 5.5 (Max) by Anthropic or Mistral Small 3.2 by Mistral? 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
Claude Haiku 5.5 (Max) scores 36.4 points higher (43.4 vs 7.0) but costs 2.7× as much to run the benchmark ($330 vs $122; both mid-range class). Pick Claude Haiku 5.5 (Max) when the extra intelligence is worth the premium, otherwise Mistral Small 3.2.
| Metric | Claude Haiku 5.5 (Max) | Mistral Small 3.2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.4 | 7.0 | −83.9% Mistral Small 3.2 is 83.9% less intelligent |
| Total AA cost (lower is better) | $330.25 | $121.78 | −63.1% Mistral Small 3.2 is 63.1% cheaper |
| End-to-end time (lower is better) | 318.47s | 10.52s | −96.7% Mistral Small 3.2 is 96.7% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.07 / $0.20 | |
| Input modalities | Text, Image | Text, Image |
Mistral Small 3.2 vs Claude Haiku 5.5 (Max): 83.9% less intelligence, 63.1% less cost to run the AA benchmark, and 96.7% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Haiku 5.5 (Max) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- Mistral Small 3.2 is off the frontier: at the same or lower cost, MiMo-V2.6-Flash scores 37.90 for $110.
Claude Haiku 5.5 (Max)Mistral Small 3.2Today'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/claude-haiku-5-5/mistral-small-3-2 · Markdown: /api/v1/compare/claude-haiku-5-5/mistral-small-3-2?format=md · llms.txt · agent skill