Claude 3.5 HaikuvsGPT-4o mini
Claude 3.5 Haiku | GPT-4o mini | |
|---|---|---|
| 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. | 50%Best | 2% |
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. | 40.6% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 41.6%Best | 40.2% |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Oct 22 2024 | Jul 18 2024 |
| Access | Proprietary | Proprietary |
Which is better: Claude 3.5 Haiku or GPT-4o mini?
Claude 3.5 Haiku leads GPT-4o mini on 2 of the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). GPT-4o mini shipped 96 days before Claude 3.5 Haiku, 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 Haiku leads at 50% vs GPT-4o mini at 2%. On GPQA Diamond, Claude 3.5 Haiku leads at 41.6% vs GPT-4o mini at 40.2%.
Frequently asked questions
Claude 3.5 Haiku was released by Anthropic on Oct 22 2024.
GPT-4o mini was released by OpenAI on Jul 18 2024.
Claude 3.5 Haiku leads on GPQA Diamond — Claude 3.5 Haiku 41.6% vs GPT-4o mini 40.2%.
Other comparisons
Claude 3.5 HaikuvsGemini 3.6 FlashGPT-4o minivsGemini 3.6 FlashClaude 3.5 HaikuvsMuse GlimmerGPT-4o minivsMuse GlimmerClaude 3.5 HaikuvsGrok 4.5GPT-4o minivsGrok 4.5Claude 3.5 HaikuvsDeepSeek-V4-Flash-0731GPT-4o minivsDeepSeek-V4-Flash-0731Claude 3.5 HaikuvsMistral Medium 3.5GPT-4o minivsMistral Medium 3.5Claude 3.5 HaikuvsKimi K3GPT-4o minivsKimi K3