Claude 3 HaikuvsDeepSeek-V3.2
Claude 3 Haiku | DeepSeek-V3.2 | |
|---|---|---|
| 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% | 13%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. | — | 1361 |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Mar 4 2024 | Dec 1 2025 |
| Access | Proprietary | Open Weight |
Which is better: Claude 3 Haiku or DeepSeek-V3.2?
DeepSeek-V3.2 leads Claude 3 Haiku on 1 of the 1 benchmark they both report (BullshitBench v2). Claude 3 Haiku shipped 637 days before DeepSeek-V3.2, so benchmark comparisons should account for the intervening progress.
Claude 3 Haiku is proprietary, while DeepSeek-V3.2 is open weight.
On BullshitBench v2, DeepSeek-V3.2 leads at 13% vs Claude 3 Haiku at 10%.
Frequently asked questions
Claude 3 Haiku was released by Anthropic on Mar 4 2024.
DeepSeek-V3.2 was released by DeepSeek on Dec 1 2025.
Claude 3 Haiku is a proprietary model released by Anthropic. DeepSeek-V3.2 is an open weight model released by DeepSeek.
Other comparisons
Claude 3 HaikuvsGPT-5.6-CyberDeepSeek-V3.2vsGPT-5.6-CyberClaude 3 HaikuvsGemini 3.7 FlashDeepSeek-V3.2vsGemini 3.7 FlashClaude 3 HaikuvsMuse GlimmerDeepSeek-V3.2vsMuse GlimmerClaude 3 HaikuvsGrok 4.6DeepSeek-V3.2vsGrok 4.6Claude 3 HaikuvsMistral Medium 3.5DeepSeek-V3.2vsMistral Medium 3.5Claude 3 HaikuvsKimi K3DeepSeek-V3.2vsKimi K3