← comparisons · head to head
DeepSeek V4 Pro vs Claude Opus 5
Claude Opus 5 scores higher than DeepSeek V4 Pro on all 6 public leaderboards that rate both. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, DeepSeek V4 Pro is at 28.8 and Claude Opus 5 at 85.9 (out of 100).
Scores as published by each board; table composed September 25, 2026.
Get the next launch alert, free →
Leaderboard by leaderboard
| Board | DeepSeek V4 Pro | Claude Opus 5 | Higher |
|---|---|---|---|
| LMArena Elo (community votes) | 1,580.5 | 1,692.4 | Claude Opus 5 |
| LiveBench global average (0-100) | 77.4 | 80.1 | Claude Opus 5 |
| SimpleBench AVG@5 % (private set) | 50.9 | 80.6 | Claude Opus 5 |
| LLM Stats LLM Stats Score · composite (0-100), their rendered top 15 | 51.1 | 54.8 | Claude Opus 5 |
| Vals AI Vals Index accuracy % · weighted finance + coding tasks | 52.4 | 67.2 | Claude Opus 5 |
| Artificial Analysis intelligence index · measured runs only | 36 | 50.8 | Claude Opus 5 |
Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.
DeepSeek V4 Pro at a glance
- Developer
- DeepSeek
- Status
- Live since April 24, 2026
- API price
- $0.435 input / $0.87 output per 1M tokens · DeepSeek, deepseek-v4-pro
- Context window
- 1M tokens
Live · open weights · superseded by V4.1 Flash — per DeepSeek's own changelog rather than our own reading, deepseek-v4-flash routes to V4.1 Flash; the matching deepseek-v4-pro cutover set for 04:00 UTC Sep 14 was reversed on its eve and V4 Pro is still served at unchanged billing, which is search-grade too — but our own bench refresh still scored deepseek-v4-pro-0813 as a separate model on Sep 16 · our sweep read the bare deepseek-flash alias on Sep 10 at $0.15/$0.60 per 1M, 1M ctx.
DeepSeek V4-Pro lands at $0.435/$0.87 — and "model names remain unchanged" hides a 2.7x price fork
2026-08-13 · DeepSeek launched V4-Pro today on app, web and API. The headline features are agent upgrades, selectable reasoning effort across V4-Pro and V4-Flash, and native OpenAI Responses API support optimised for Codex. The line worth reading twice is the quiet one: "Model names remain unchanged."
Claude Opus 5 at a glance
- Developer
- Anthropic
- Status
- Live since July 24, 2026
- API price
- $5 input / $25 output per 1M tokens · Anthropic, claude-opus-5
- Context window
- 1M tokens
Live — detected 16:51 UTC Jul 24, alert fired 61s later · superseded by Opus 5.5 on Sep 22 and moved to Anthropic's legacy list; still served at $5/$25, which is now MORE than its successor.
Claude Opus 5 is live — we detected it at 16:51 UTC and had alerts out 61 seconds later
2026-07-24 · Anthropic's Claude Opus 5 went live on the public API today. Our checkers saw the id appear at 16:51:33 UTC, confirmed it on the next 60-second sweep, and the alert blast went out at 16:52:34 — sixty-one seconds from first sighting to inbox.
DeepSeek V4 Pro vs Claude Opus 5: quick answers
Which is better, DeepSeek V4 Pro or Claude Opus 5?
It depends on what you measure. Claude Opus 5 scores higher than DeepSeek V4 Pro on all 6 public leaderboards that rate both. Claude Opus 5's widest lead is on LLM Stats. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, DeepSeek V4 Pro is at 28.8 and Claude Opus 5 at 85.9 (out of 100).
Which is newer, DeepSeek V4 Pro or Claude Opus 5?
Claude Opus 5. It went live on July 24, 2026, 91 days after DeepSeek V4 Pro (April 24, 2026).
Which is cheaper, DeepSeek V4 Pro or Claude Opus 5?
DeepSeek V4 Pro is cheaper on both input and output. On each vendor's own API, DeepSeek V4 Pro is $0.435 input / $0.87 output per million tokens and Claude Opus 5 is $5 input / $25 output per million tokens. Prices as published in the models.dev catalog, as of 2026-09-25.
Which has the bigger context window, DeepSeek V4 Pro or Claude Opus 5?
Neither. Both take 1M tokens.
Who makes DeepSeek V4 Pro and Claude Opus 5?
DeepSeek V4 Pro is from DeepSeek; Claude Opus 5 is from Anthropic.
Where do these numbers come from?
Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed September 25, 2026). Boards measure different things, so raw scores are only comparable within a row.
More comparisons
Hear the minute the next one drops. Free.
A free Chrome push the moment a new model answers on a public API, an email about 15 minutes later. Texts or a phone call on paid plans.
- Free forever
- No card
- Unsubscribe in one click
Also: the bench index · API pricing · the wire