DeepSeek-V4-ProvsQwen3.8-Max
DeepSeek-V4-Pro | Qwen3.8-Max | |
|---|---|---|
| Specifications | ||
Parameters | — | 2.4T |
Context window | — | 1M |
| 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. | 14% | — |
Agentic coding SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | — | 67.7% |
Research reproduction PaperBenchreproducing the results of an ML research paper end to end | — | 93% |
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. | 93.5% | — |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 86.6% |
Professional tool use JobBenchTests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | — | 53.4% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 90.1% | — |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | — | 86.1% |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 88.4% |
Visual reasoning BabyVisionTests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better. | — | 82% |
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. | 1457 | 1497Best |
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. | 1446 | 1667Best |
| Overview | ||
| Company | DeepSeek | Qwen |
| Release date | Apr 24 2026 | Aug 3 2026 |
| Access | Open Weight | Proprietary |
Which is better: DeepSeek-V4-Pro or Qwen3.8-Max?
Qwen3.8-Max leads DeepSeek-V4-Pro on 2 of the 2 benchmarks they both report (Arena Elo (Text), Arena Elo (Code)). DeepSeek-V4-Pro shipped 101 days before Qwen3.8-Max, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Pro is open weight, while Qwen3.8-Max is proprietary.
On Arena Elo (Text), Qwen3.8-Max leads at 1497 vs DeepSeek-V4-Pro at 1457. On Arena Elo (Code), Qwen3.8-Max leads at 1667 vs DeepSeek-V4-Pro at 1446.
Frequently asked questions
DeepSeek-V4-Pro was released by DeepSeek on Apr 24 2026.
Qwen3.8-Max was released by Qwen on Aug 3 2026.
DeepSeek-V4-Pro is an open weight model released by DeepSeek. Qwen3.8-Max is a proprietary model released by Qwen.
Other comparisons
DeepSeek-V4-ProvsClaude Opus 5Qwen3.8-MaxvsClaude Opus 5DeepSeek-V4-ProvsGPT-5.6 SolQwen3.8-MaxvsGPT-5.6 SolDeepSeek-V4-ProvsGemini 3.6 FlashQwen3.8-MaxvsGemini 3.6 FlashDeepSeek-V4-ProvsMuse Spark 1.2Qwen3.8-MaxvsMuse Spark 1.2DeepSeek-V4-ProvsGrok 4.5Qwen3.8-MaxvsGrok 4.5DeepSeek-V4-ProvsMistral Medium 3.5Qwen3.8-MaxvsMistral Medium 3.5