Claude 3 OpusvsClaude Opus 4
Claude 3 Opus | Claude Opus 4 | |
|---|---|---|
| Benchmarks | ||
SWE-Bench VerifiedCoding — Real 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. | 33% | 72.5% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 50.4% | 79.6% |
| BenchmarksPublished by one model only | ||
BullshitBench v2Nonsense detection — Given 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. | — | 34% |
| Overview | ||
| Company | Anthropic | Anthropic |
| Release date | Mar 4 2024 | May 22 2025 |
| Access | Proprietary | Proprietary |
Frequently asked questions
Claude Opus 4 leads Claude 3 Opus on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). Claude 3 Opus shipped 444 days before Claude Opus 4, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On SWE-Bench Verified, Claude Opus 4 leads at 72.5% vs Claude 3 Opus at 33%. On GPQA Diamond, Claude Opus 4 leads at 79.6% vs Claude 3 Opus at 50.4%.
Claude 3 Opus was released by Anthropic on Mar 4 2024.
Claude Opus 4 was released by Anthropic on May 22 2025.
Claude Opus 4 leads on SWE-Bench Verified — Claude 3 Opus 33% vs Claude Opus 4 72.5%.
Claude Opus 4 leads on GPQA Diamond — Claude 3 Opus 50.4% vs Claude Opus 4 79.6%.