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. | 33.3% | 50.4% |
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. | 10% | — |
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% |
| Overview | ||
| Company | Anthropic | Anthropic |
| Release date | Mar 4 2024 | Mar 4 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude 3 HaikuvsGPT-6.1 SolClaude 3 OpusvsGPT-6.1 SolClaude 3 HaikuvsGemini 4 ArgonClaude 3 OpusvsGemini 4 ArgonClaude 3 HaikuvsMuse WonderClaude 3 OpusvsMuse WonderClaude 3 HaikuvsGrok 4.7Claude 3 OpusvsGrok 4.7Claude 3 HaikuvsDeepSeek-V4.1-FlashClaude 3 OpusvsDeepSeek-V4.1-FlashClaude 3 HaikuvsMistral Large 4Claude 3 OpusvsMistral Large 4Frequently asked questions
Claude 3 Opus leads Claude 3 Haiku on 1 of the 1 benchmark they both report (GPQA Diamond). Both models were released on the same day — Mar 4 2024.
Published specifications for these two models are limited — see each model page for the latest details.
On GPQA Diamond, Claude 3 Opus leads at 50.4% vs Claude 3 Haiku at 33.3%.