Claude 3 HaikuvsLLaMA 4 Scout
Claude 3 Haiku | LLaMA 4 Scout | |
|---|---|---|
| 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% | 19%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% | — |
| Overview | ||
| Company | Anthropic | Meta |
| Release date | Mar 4 2024 | Apr 5 2025 |
| Access | Proprietary | Open Weight |
Which is better: Claude 3 Haiku or LLaMA 4 Scout?
LLaMA 4 Scout leads Claude 3 Haiku on 1 of the 1 benchmark they both report (BullshitBench v2). Claude 3 Haiku shipped 397 days before LLaMA 4 Scout, so benchmark comparisons should account for the intervening progress.
Claude 3 Haiku is proprietary, while LLaMA 4 Scout is open weight.
On BullshitBench v2, LLaMA 4 Scout leads at 19% vs Claude 3 Haiku at 10%.
Frequently asked questions
Claude 3 Haiku was released by Anthropic on Mar 4 2024.
LLaMA 4 Scout was released by Meta on Apr 5 2025.
Claude 3 Haiku is a proprietary model released by Anthropic. LLaMA 4 Scout is an open weight model released by Meta.
Other comparisons
Claude 3 HaikuvsGPT-5.6 SolLLaMA 4 ScoutvsGPT-5.6 SolClaude 3 HaikuvsGemini 3.6 FlashLLaMA 4 ScoutvsGemini 3.6 FlashClaude 3 HaikuvsGrok 4.5LLaMA 4 ScoutvsGrok 4.5Claude 3 HaikuvsDeepSeek-V4-Flash-0731LLaMA 4 ScoutvsDeepSeek-V4-Flash-0731Claude 3 HaikuvsMistral Medium 3.5LLaMA 4 ScoutvsMistral Medium 3.5Claude 3 HaikuvsKimi K3LLaMA 4 ScoutvsKimi K3