Claude Haiku 5.5 (Low) vs Mistral Large 4 Preview
Which is better for the money: Claude Haiku 5.5 (Low) by Anthropic or Mistral Large 4 Preview by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-29.
Trade-off
Verdict
Depends on your budget
Mistral Large 4 Preview scores 6.7 points higher (25.3 vs 18.6) but costs 74× as much to run the benchmark ($2923 vs $39.6; flagship vs budget cost classes). They are not alternatives at one budget: pick Mistral Large 4 Preview when you need intelligence above 18.6, and Claude Haiku 5.5 (Low) when 18.6 is enough.
| Metric | Claude Haiku 5.5 (Low) | Mistral Large 4 Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 18.6 | 25.3 | +36.0% Mistral Large 4 Previ… is 36.0% more intelligent |
| Total AA cost (lower is better) | $39.60 | $2,923.39 | +7282.3% Mistral Large 4 Previ… is 74× more expensive |
| End-to-end time (lower is better) | 9.81s | 25.54s | +160.3% Mistral Large 4 Previ… is 160.3% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.70 / $2.10 | |
| Input modalities | Text, Image | Text, Image |
Mistral Large 4 Preview vs Claude Haiku 5.5 (Low): 36.0% more intelligence, 7282.3% more cost to run the AA benchmark, and 160.3% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Haiku 5.5 (Low) is on today's frontier: nothing is both smarter and cheaper.
- Mistral Large 4 Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 54.50 for $1124.
Claude Haiku 5.5 (Low)Mistral Large 4 PreviewToday's Pareto 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-low/mistral-large-4-preview · Markdown: /api/v1/compare/claude-haiku-5-5-low/mistral-large-4-preview?format=md · llms.txt · agent skill