Claude 3 Haiku vs GPT-5
Anthropic Claude 3 Haiku | OpenAI GPT-5 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Mar 4 2024 | Aug 7 2025 |
| Access | Proprietary | Proprietary |
| 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% | 21%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% | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | — | 1394 |
| Timeline | ||
| Release gap | Claude 3 Haiku shipped 521 days before GPT-5 | |
Which is better: Claude 3 Haiku or GPT-5?
GPT-5 leads Claude 3 Haiku on 1 of the 1 benchmark they both report (BullshitBench v2). Claude 3 Haiku shipped 521 days before GPT-5, 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-5 leads at 21% vs Claude 3 Haiku at 10%.
Frequently asked questions
Claude 3 Haiku was released by Anthropic on Mar 4 2024.
GPT-5 was released by OpenAI on Aug 7 2025.
Other comparisons
Claude 3 Haiku vs Gemini OmniGPT-5 vs Gemini OmniClaude 3 Haiku vs Muse Spark 1.1GPT-5 vs Muse Spark 1.1Claude 3 Haiku vs Grok 4.5GPT-5 vs Grok 4.5Claude 3 Haiku vs DeepSeek-V4-ProGPT-5 vs DeepSeek-V4-ProClaude 3 Haiku vs Mistral Medium 3.5GPT-5 vs Mistral Medium 3.5Claude 3 Haiku vs Kimi K2.7 CodeGPT-5 vs Kimi K2.7 Code