AI Model Release Tracker - Analytics

Claude 3.5 HaikuvsDeepSeek-V4-Flash

Claude 3.5 Haiku
DeepSeek-V4-Flash
Benchmarks
Nonsense detection
BullshitBench v2
50%Best
18%
Coding
SWE-Bench Verified
40.6%
Competitive coding
LiveCodeBench
91.6%
Science
GPQA Diamond
41.6%
88.1%Best
Overview
CompanyAnthropicDeepSeek
Release dateOct 22 2024Apr 24 2026
AccessProprietaryOpen Weight

Which is better: Claude 3.5 Haiku or DeepSeek-V4-Flash?

Claude 3.5 Haiku and DeepSeek-V4-Flash are evenly matched across the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). Claude 3.5 Haiku shipped 549 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.

Claude 3.5 Haiku is proprietary, while DeepSeek-V4-Flash is open weight.

On BullshitBench v2, Claude 3.5 Haiku leads at 50% vs DeepSeek-V4-Flash at 18%. On GPQA Diamond, DeepSeek-V4-Flash leads at 88.1% vs Claude 3.5 Haiku at 41.6%.

Frequently asked questions

Claude 3.5 Haiku was released by Anthropic on Oct 22 2024.

DeepSeek-V4-Flash was released by DeepSeek on Apr 24 2026.

DeepSeek-V4-Flash leads on GPQA Diamond — Claude 3.5 Haiku 41.6% vs DeepSeek-V4-Flash 88.1%.

Claude 3.5 Haiku is a proprietary model released by Anthropic. DeepSeek-V4-Flash is an open weight model released by DeepSeek.

Other comparisons