Compare AI models
| 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. | $0.03Relace | $0.042Darkbloom |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $0.084StreamLake | $0.22Darkbloom |
| 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. | 18% | 25% |
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. | 91.6% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 88.1% | — |
| Overview | ||
| Company | DeepSeek | |
| Release date | Apr 24 2026 | Apr 2 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-FlashvsClaude Haiku 5.5Gemma 4vsClaude Haiku 5.5DeepSeek-V4-FlashvsGPT-6.1 SolGemma 4vsGPT-6.1 SolDeepSeek-V4-FlashvsMuse Spark 1.3Gemma 4vsMuse Spark 1.3DeepSeek-V4-FlashvsGrok 4.7Gemma 4vsGrok 4.7DeepSeek-V4-FlashvsMistral Large 4Gemma 4vsMistral Large 4DeepSeek-V4-FlashvsKimi K3Gemma 4vsKimi K3Frequently asked questions
Gemma 4 leads DeepSeek-V4-Flash on 1 of the 1 benchmark they both report (BullshitBench v2). Gemma 4 shipped 22 days before DeepSeek-V4-Flash, 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, Gemma 4 leads at 25% vs DeepSeek-V4-Flash at 18%.