AI Model Release Tracker - Analytics

Claude 3 OpusvsDeepSeek-V4-Pro

Claude 3 Opus
DeepSeek-V4-Pro
Benchmarks
Nonsense detection
BullshitBench v2
14%
Coding
SWE-Bench Verified
33%
Competitive coding
LiveCodeBench
93.5%
Web browsing
BrowseComp
83.4%
Science
GPQA Diamond
50.4%
90.1%Best
Community preference (code)
Arena Elo (Code)
1457
Overview
CompanyAnthropicDeepSeek
Release dateMar 4 2024Apr 24 2026
AccessProprietaryOpen Weight

Which is better: Claude 3 Opus or DeepSeek-V4-Pro?

DeepSeek-V4-Pro leads Claude 3 Opus on 1 of the 1 benchmark they both report (GPQA Diamond). Claude 3 Opus shipped 781 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.

Claude 3 Opus is proprietary, while DeepSeek-V4-Pro is open weight.

On GPQA Diamond, DeepSeek-V4-Pro leads at 90.1% vs Claude 3 Opus at 50.4%.

Frequently asked questions

Claude 3 Opus was released by Anthropic on Mar 4 2024.

DeepSeek-V4-Pro was released by DeepSeek on Apr 24 2026.

DeepSeek-V4-Pro leads on GPQA Diamond — Claude 3 Opus 50.4% vs DeepSeek-V4-Pro 90.1%.

Claude 3 Opus is a proprietary model released by Anthropic. DeepSeek-V4-Pro is an open weight model released by DeepSeek.

Other comparisons