DeepSeek-V4-ProvsCodestral 22B
DeepSeek-V4-Pro | Codestral 22B | |
|---|---|---|
| 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. | 14% | — |
Competitive coding LiveCodeBenchCoding 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% | — |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 90.1% | — |
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. | 1457 | — |
| Timeline | ||
| Release gap | Codestral 22B shipped 695 days before DeepSeek-V4-Pro | |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Apr 24 2026 | May 29 2024 |
| Access | Open Weight | Proprietary |
Which is better: DeepSeek-V4-Pro or Codestral 22B?
DeepSeek-V4-Pro and Codestral 22B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral 22B shipped 695 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Pro is open weight, while Codestral 22B is proprietary.
Direct benchmark comparisons are unavailable — DeepSeek-V4-Pro and Codestral 22B don't publish scores on any of the same benchmarks.
Frequently asked questions
DeepSeek-V4-Pro was released by DeepSeek on Apr 24 2026.
Codestral 22B was released by Mistral on May 29 2024.
DeepSeek-V4-Pro is an open weight model released by DeepSeek. Codestral 22B is a proprietary model released by Mistral.
Other comparisons
DeepSeek-V4-ProvsClaude Sonnet 5Codestral 22BvsClaude Sonnet 5DeepSeek-V4-ProvsGPT-5.6 SolCodestral 22BvsGPT-5.6 SolDeepSeek-V4-ProvsGemini 3.6 FlashCodestral 22BvsGemini 3.6 FlashDeepSeek-V4-ProvsMuse Spark 1.1Codestral 22BvsMuse Spark 1.1DeepSeek-V4-ProvsGrok 4.5Codestral 22BvsGrok 4.5DeepSeek-V4-ProvsKimi K3Codestral 22BvsKimi K3