Compare AI models
| 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% |
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 | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude 3 OpusvsGPT-6.1 SolClaude Opus 4vsGPT-6.1 SolClaude 3 OpusvsGemini 4 ArgonClaude Opus 4vsGemini 4 ArgonClaude 3 OpusvsMuse WonderClaude Opus 4vsMuse WonderClaude 3 OpusvsGrok 4.7Claude Opus 4vsGrok 4.7Claude 3 OpusvsDeepSeek-V4.1-FlashClaude Opus 4vsDeepSeek-V4.1-FlashClaude 3 OpusvsMistral Large 4Claude Opus 4vsMistral Large 4Frequently 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%.