Claude 3.5 HaikuvsDeepSeek-V4-Pro
Claude 3.5 Haiku | DeepSeek-V4-Pro | |
|---|---|---|
| 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. | 50% | 14% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 41.6% | 90.1% |
| BenchmarksPublished by one model only | ||
SWE-Bench VerifiedCoding — Real 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% | — |
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. | — | 93.5% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 83.4% |
Arena Elo (Text)Community preference — Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | — | 1457 |
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. | — | 1446 |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Oct 22 2024 | Apr 24 2026 |
| Access | Proprietary | Open Weight |
Frequently asked questions
Claude 3.5 Haiku and DeepSeek-V4-Pro are evenly matched across the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). Claude 3.5 Haiku shipped 549 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
Claude 3.5 Haiku is proprietary, while DeepSeek-V4-Pro is open weight.
On BullshitBench v2, Claude 3.5 Haiku leads at 50% vs DeepSeek-V4-Pro at 14%. On GPQA Diamond, DeepSeek-V4-Pro leads at 90.1% vs Claude 3.5 Haiku at 41.6%.
Claude 3.5 Haiku was released by Anthropic on Oct 22 2024.
DeepSeek-V4-Pro was released by DeepSeek on Apr 24 2026.
DeepSeek-V4-Pro leads on GPQA Diamond — Claude 3.5 Haiku 41.6% vs DeepSeek-V4-Pro 90.1%.
Claude 3.5 Haiku is a proprietary model released by Anthropic. DeepSeek-V4-Pro is an open weight model released by DeepSeek.