Claude 3.5 SonnetvsGPT-4o
Claude 3.5 Sonnet | GPT-4o | |
|---|---|---|
| Specifications | ||
Context window | — | 128k |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given 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. | 45%Best | 12% |
Coding SWE-Bench VerifiedReal 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% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 59.4%Best | 49.9% |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Jun 20 2024 | May 13 2024 |
| Access | Proprietary | Proprietary |
Which is better: Claude 3.5 Sonnet or GPT-4o?
Claude 3.5 Sonnet leads GPT-4o on 2 of the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). GPT-4o shipped 38 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 BullshitBench v2, Claude 3.5 Sonnet leads at 45% vs GPT-4o at 12%. On GPQA Diamond, Claude 3.5 Sonnet leads at 59.4% vs GPT-4o at 49.9%.
Frequently asked questions
Claude 3.5 Sonnet was released by Anthropic on Jun 20 2024.
GPT-4o was released by OpenAI on May 13 2024.
Claude 3.5 Sonnet leads on GPQA Diamond — Claude 3.5 Sonnet 59.4% vs GPT-4o 49.9%.
Other comparisons
Claude 3.5 SonnetvsGemini 3.7 FlashGPT-4ovsGemini 3.7 FlashClaude 3.5 SonnetvsMuse GlimmerGPT-4ovsMuse GlimmerClaude 3.5 SonnetvsGrok 4.6GPT-4ovsGrok 4.6Claude 3.5 SonnetvsDeepSeek-V4-Pro-0813GPT-4ovsDeepSeek-V4-Pro-0813Claude 3.5 SonnetvsMistral Medium 3.5GPT-4ovsMistral Medium 3.5Claude 3.5 SonnetvsKimi K3GPT-4ovsKimi K3