Claude 3 HaikuvsDeepSeek-V4-Flash
Claude 3 Haiku | DeepSeek-V4-Flash | |
|---|---|---|
| Benchmarks | ||
BullshitBench v2Nonsense detection — Given 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% | 18% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 33.3% | 88.1% |
| BenchmarksPublished by one model only | ||
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 91.6% |
Arena Elo (Code)Community preference (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. | — | 1577 |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Mar 4 2024 | Apr 24 2026 |
| Access | Proprietary | Open Weight |
Frequently asked questions
DeepSeek-V4-Flash leads Claude 3 Haiku on 2 of the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). Claude 3 Haiku shipped 781 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.
Claude 3 Haiku is proprietary, while DeepSeek-V4-Flash is open weight.
On BullshitBench v2, DeepSeek-V4-Flash leads at 18% vs Claude 3 Haiku at 10%. On GPQA Diamond, DeepSeek-V4-Flash leads at 88.1% vs Claude 3 Haiku at 33.3%.
Claude 3 Haiku was released by Anthropic on Mar 4 2024.
DeepSeek-V4-Flash was released by DeepSeek on Apr 24 2026.
DeepSeek-V4-Flash leads on GPQA Diamond — Claude 3 Haiku 33.3% vs DeepSeek-V4-Flash 88.1%.
Claude 3 Haiku is a proprietary model released by Anthropic. DeepSeek-V4-Flash is an open weight model released by DeepSeek.