Claude Opus 5 (Medium) vs DeepSeek V4 Pro 0813 (Max)
Which is better for the money: Claude Opus 5 (Medium) by Anthropic or DeepSeek V4 Pro 0813 (Max) by DeepSeek? 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 Opus 5 (Medium) scores 8.8 points higher (44.8 vs 36.0) but costs 2.4× as much to run the benchmark ($2732 vs $1122; flagship vs premium cost classes). Pick Claude Opus 5 (Medium) when the extra intelligence is worth the premium, otherwise DeepSeek V4 Pro 0813 (Max).
| Metric | Claude Opus 5 (Medium) | DeepSeek V4 Pro 0813 (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 44.8 | 36.0 | −19.6% DeepSeek V4 Pro 0813 … is 19.6% less intelligent |
| Total AA cost (lower is better) | $2,731.91 | $1,122.27 | −58.9% DeepSeek V4 Pro 0813 … is 58.9% cheaper |
| End-to-end time (lower is better) | 12.73s | 25.92s | +103.6% DeepSeek V4 Pro 0813 … is 103.6% slower |
| Price per 1M tokens (in / out) | $5.00 / $25.0 | $1.32 / $3.96 | |
| Input modalities | Text, Image | Text |
DeepSeek V4 Pro 0813 (Max) vs Claude Opus 5 (Medium): 19.6% less intelligence, 58.9% less cost to run the AA benchmark, and 103.6% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Opus 5 (Medium) is off the frontier: at the same or lower cost, Claude Opus 5.5 (High, Default Fallback) scores 53.60 for $2172.
- DeepSeek V4 Pro 0813 (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Claude Opus 5 (Medium)DeepSeek V4 Pro 0813 (Max)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-opus-5-medium/deepseek-v4-pro · Markdown: /api/v1/compare/claude-opus-5-medium/deepseek-v4-pro?format=md · llms.txt · agent skill