DeepSeek-V4-ProvsGrok 4.1 Fast
DeepSeek-V4-Pro | Grok 4.1 Fast | |
|---|---|---|
| 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. | 14% | 19% |
| 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. | 93.5% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 90.1% | — |
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 | DeepSeek | SpaceXAI |
| Release date | Apr 24 2026 | Nov 19 2025 |
| Access | Open Weight | Proprietary |
Frequently asked questions
Grok 4.1 Fast leads DeepSeek-V4-Pro on 1 of the 1 benchmark they both report (BullshitBench v2). Grok 4.1 Fast shipped 156 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Pro is open weight, while Grok 4.1 Fast is proprietary.
On BullshitBench v2, Grok 4.1 Fast leads at 19% vs DeepSeek-V4-Pro at 14%.
DeepSeek-V4-Pro was released by DeepSeek on Apr 24 2026.
Grok 4.1 Fast was released by SpaceXAI on Nov 19 2025.
DeepSeek-V4-Pro is an open weight model released by DeepSeek. Grok 4.1 Fast is a proprietary model released by SpaceXAI.
Other comparisons
DeepSeek-V4-ProvsClaude Opus 5Grok 4.1 FastvsClaude Opus 5DeepSeek-V4-ProvsGPT-5.6-CyberGrok 4.1 FastvsGPT-5.6-CyberDeepSeek-V4-ProvsGemini 3.7 FlashGrok 4.1 FastvsGemini 3.7 FlashDeepSeek-V4-ProvsMuse GlimmerGrok 4.1 FastvsMuse GlimmerDeepSeek-V4-ProvsMistral Medium 3.5Grok 4.1 FastvsMistral Medium 3.5DeepSeek-V4-ProvsKimi K3Grok 4.1 FastvsKimi K3