Claude Opus 4.6vsDeepSeek-V4-Flash
Claude Opus 4.6 | DeepSeek-V4-Flash | |
|---|---|---|
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 87%Best | 18% |
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 80.8% | — |
Next.js coding Next.js EvalsVercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 75% | — |
Competitive coding LiveCodeBenchCoding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 91.6% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 83.7% | — |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | 53% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.3%Best | 88.1% |
Community preference Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | 1504 | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1543 | — |
| Timeline | ||
| Release gap | Claude Opus 4.6 shipped 78 days before DeepSeek-V4-Flash | |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Feb 5 2026 | Apr 24 2026 |
| Access | Proprietary | Open Weight |
Which is better: Claude Opus 4.6 or DeepSeek-V4-Flash?
Claude Opus 4.6 leads DeepSeek-V4-Flash on 2 of the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). Claude Opus 4.6 shipped 78 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.
Claude Opus 4.6 is proprietary, while DeepSeek-V4-Flash is open weight.
On BullshitBench v2, Claude Opus 4.6 leads at 87% vs DeepSeek-V4-Flash at 18%. On GPQA Diamond, Claude Opus 4.6 leads at 91.3% vs DeepSeek-V4-Flash at 88.1%.
Frequently asked questions
Claude Opus 4.6 was released by Anthropic on Feb 5 2026.
DeepSeek-V4-Flash was released by DeepSeek on Apr 24 2026.
Claude Opus 4.6 leads on GPQA Diamond — Claude Opus 4.6 91.3% vs DeepSeek-V4-Flash 88.1%.
Claude Opus 4.6 is a proprietary model released by Anthropic. DeepSeek-V4-Flash is an open weight model released by DeepSeek.