Claude Haiku 5.5 (Medium) vs DeepSeek V4.1 Flash 1017 (Non-reasoning)
Which is better for the money: Claude Haiku 5.5 (Medium) by Anthropic or DeepSeek V4.1 Flash 1017 (Non-reasoning) by DeepSeek? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-31.
Clear winner
Verdict
Pick Claude Haiku 5.5 (Medium)
DeepSeek V4.1 Flash 1017 (Non-reasoning) vs Claude Haiku 5.5 (Medium): 24.8% less intelligence, 326.7% more cost to run the AA benchmark, and 72.8% faster end-to-end.
| Metric | Claude Haiku 5.5 (Medium) | DeepSeek V4.1 Flash 1017 (Non-reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 24.6 | 18.5 | −24.8% DeepSeek V4.1 Flash 1… is 24.8% less intelligent |
| Total AA cost (lower is better) | $72.70 | $310.24 | +326.7% DeepSeek V4.1 Flash 1… is 4.3× more expensive |
| End-to-end time (lower is better) | 15.13s | 4.11s | −72.8% DeepSeek V4.1 Flash 1… is 72.8% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.30 / $1.20 | |
| Input modalities | Text, Image | Text, Image |
Today's Pareto frontier
Against the frontier
- Claude Haiku 5.5 (Medium) is on today's frontier: nothing is both smarter and cheaper.
- DeepSeek V4.1 Flash 1017 (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Terra (High) scores 42.30 for $267.
Claude Haiku 5.5 (Medium)DeepSeek V4.1 Flash 1017 (Non-reasoning)Today'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-medium/deepseek-v4-1-flash-1017-non-reasoning · Markdown: /api/v1/compare/claude-haiku-5-5-medium/deepseek-v4-1-flash-1017-non-reasoning?format=md · llms.txt · agent skill