Compare AI models
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 40.4% | 59.4% |
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. | — | 46% |
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. | — | 33.4% |
| Overview | ||
| Company | Anthropic | Anthropic |
| Release date | Mar 4 2024 | Jun 20 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude 3 SonnetvsGPT-6.1 SolClaude 3.5 SonnetvsGPT-6.1 SolClaude 3 SonnetvsGemini 4 ArgonClaude 3.5 SonnetvsGemini 4 ArgonClaude 3 SonnetvsMuse WonderClaude 3.5 SonnetvsMuse WonderClaude 3 SonnetvsGrok 4.7Claude 3.5 SonnetvsGrok 4.7Claude 3 SonnetvsDeepSeek-V4.1-FlashClaude 3.5 SonnetvsDeepSeek-V4.1-FlashClaude 3 SonnetvsMistral Large 4Claude 3.5 SonnetvsMistral Large 4Frequently asked questions
Claude 3.5 Sonnet leads Claude 3 Sonnet on 1 of the 1 benchmark they both report (GPQA Diamond). Claude 3 Sonnet shipped 108 days before Claude 3.5 Sonnet, 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 GPQA Diamond, Claude 3.5 Sonnet leads at 59.4% vs Claude 3 Sonnet at 40.4%.