DeepSeek-V4-ProvsLLaMA 4 Scout
DeepSeek-V4-Pro | LLaMA 4 Scout | |
|---|---|---|
| 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. | $0.7078StreamLake | $0.10DeepInfra |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $1.4157StreamLake | $0.30DeepInfra |
| 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% | — |
| Overview | ||
| Company | DeepSeek | Meta |
| Release date | Apr 24 2026 | Apr 5 2025 |
| Access | Open Weight | Open Weight |
Other comparisons
DeepSeek-V4-ProvsClaude Fable 5.1LLaMA 4 ScoutvsClaude Fable 5.1DeepSeek-V4-ProvsGPT-6 AstraLLaMA 4 ScoutvsGPT-6 AstraDeepSeek-V4-ProvsGemini 3.8 FlashLLaMA 4 ScoutvsGemini 3.8 FlashDeepSeek-V4-ProvsGrok 4.6LLaMA 4 ScoutvsGrok 4.6DeepSeek-V4-ProvsMistral Medium 3.5LLaMA 4 ScoutvsMistral Medium 3.5DeepSeek-V4-ProvsKimi K3LLaMA 4 ScoutvsKimi K3
Frequently asked questions
LLaMA 4 Scout leads DeepSeek-V4-Pro on 1 of the 1 benchmark they both report (BullshitBench v2). LLaMA 4 Scout shipped 384 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On BullshitBench v2, LLaMA 4 Scout leads at 19% vs DeepSeek-V4-Pro at 14%.