Claude 3 HaikuvsGPT-4o
Claude 3 Haiku | 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. | 10% | 12%Best |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 33.3% | 49.9%Best |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Mar 4 2024 | May 13 2024 |
| Access | Proprietary | Proprietary |
Which is better: Claude 3 Haiku or GPT-4o?
GPT-4o leads Claude 3 Haiku on 2 of the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). Claude 3 Haiku shipped 70 days before GPT-4o, 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, GPT-4o leads at 12% vs Claude 3 Haiku at 10%. On GPQA Diamond, GPT-4o leads at 49.9% vs Claude 3 Haiku at 33.3%.
Frequently asked questions
Claude 3 Haiku was released by Anthropic on Mar 4 2024.
GPT-4o was released by OpenAI on May 13 2024.
GPT-4o leads on GPQA Diamond — Claude 3 Haiku 33.3% vs GPT-4o 49.9%.
Other comparisons
Claude 3 HaikuvsGemini 3.6 FlashGPT-4ovsGemini 3.6 FlashClaude 3 HaikuvsMuse Spark 1.2GPT-4ovsMuse Spark 1.2Claude 3 HaikuvsGrok 4.5GPT-4ovsGrok 4.5Claude 3 HaikuvsDeepSeek-V4-Flash-0731GPT-4ovsDeepSeek-V4-Flash-0731Claude 3 HaikuvsMistral Medium 3.5GPT-4ovsMistral Medium 3.5Claude 3 HaikuvsKimi K3GPT-4ovsKimi K3