DeepSeek-V4-ProvsGrok 2.5
DeepSeek-V4-Pro | Grok 2.5 | |
|---|---|---|
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.9553StreamLake | — |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $1.9105StreamLake | — |
| BenchmarksPublished by one model only | ||
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% | — |
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% | — |
| Overview | ||
| Company | DeepSeek | SpaceXAI |
| Release date | Apr 24 2026 | Aug 23 2025 |
| Access | Open Weight | Proprietary |
Other comparisons
DeepSeek-V4-ProvsClaude Fable 5.1Grok 2.5vsClaude Fable 5.1DeepSeek-V4-ProvsGPT-6 AstraGrok 2.5vsGPT-6 AstraDeepSeek-V4-ProvsGemini 3.8 FlashGrok 2.5vsGemini 3.8 FlashDeepSeek-V4-ProvsMuse Spark 1.3Grok 2.5vsMuse Spark 1.3DeepSeek-V4-ProvsMistral Medium 3.5Grok 2.5vsMistral Medium 3.5DeepSeek-V4-ProvsKimi K3Grok 2.5vsKimi K3
Frequently asked questions
DeepSeek-V4-Pro and Grok 2.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Grok 2.5 shipped 244 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Pro is open weight, while Grok 2.5 is proprietary.
Direct benchmark comparisons are unavailable — DeepSeek-V4-Pro and Grok 2.5 don't publish scores on any of the same benchmarks.