AI Model Release Tracker - Analytics

Claude Sonnet 4.5vsDeepSeek-V4-Flash

Claude Sonnet 4.5
DeepSeek-V4-Flash
Benchmarks
Nonsense detection
BullshitBench v2
79%Best
18%
Coding
SWE-Bench Verified
77.2%
Next.js coding
Next.js Evals
50%
Competitive coding
LiveCodeBench
91.6%
Science
GPQA Diamond
83.4%
88.1%Best
Multimodal
MMMU
68%
Timeline
Release gapClaude Sonnet 4.5 shipped 207 days before DeepSeek-V4-Flash
Overview
CompanyAnthropicDeepSeek
Release dateSep 29 2025Apr 24 2026
AccessProprietaryOpen Weight

Which is better: Claude Sonnet 4.5 or DeepSeek-V4-Flash?

Claude Sonnet 4.5 and DeepSeek-V4-Flash are evenly matched across the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). Claude Sonnet 4.5 shipped 207 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.

Claude Sonnet 4.5 is proprietary, while DeepSeek-V4-Flash is open weight.

On BullshitBench v2, Claude Sonnet 4.5 leads at 79% vs DeepSeek-V4-Flash at 18%. On GPQA Diamond, DeepSeek-V4-Flash leads at 88.1% vs Claude Sonnet 4.5 at 83.4%.

Frequently asked questions

Claude Sonnet 4.5 was released by Anthropic on Sep 29 2025.

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

DeepSeek-V4-Flash leads on GPQA Diamond — Claude Sonnet 4.5 83.4% vs DeepSeek-V4-Flash 88.1%.

Claude Sonnet 4.5 is a proprietary model released by Anthropic. DeepSeek-V4-Flash is an open weight model released by DeepSeek.

Other comparisons