Compare AI models
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | — | 74B |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.45Parasail | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.9105StreamLake | — |
| $264Parasail · fp8 | — | |
| Benchmarks | ||
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4% | 66.75% |
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% | 86.43% |
CheatBenchCheating rate — Measures how often AI agents try to cheat on difficult assignments, such as reading hidden answers, copying work or manipulating grading. The overall score gives equal weight to ten categories; the sycophancy category measures how far an agent shifts its beliefs toward a user's stated views. Scores describe each model in its tested agent setup, and task success is measured separately. Lower is better. | 75.1% | — |
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% | — |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 50.98% |
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | — | 52.2% |
| Overview | ||
| Company | DeepSeek | NVIDIA |
| Release date | Apr 24 2026 | Oct 15 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-ProvsClaude Haiku 5.5Nemotron 3.5 Bolt 74BvsClaude Haiku 5.5DeepSeek-V4-ProvsGPT-6.1 SolNemotron 3.5 Bolt 74BvsGPT-6.1 SolDeepSeek-V4-ProvsGemini 4 ArgonNemotron 3.5 Bolt 74BvsGemini 4 ArgonDeepSeek-V4-ProvsMuse Spark OpenNemotron 3.5 Bolt 74BvsMuse Spark OpenDeepSeek-V4-ProvsGrok 4.7Nemotron 3.5 Bolt 74BvsGrok 4.7DeepSeek-V4-ProvsMistral Large 4Nemotron 3.5 Bolt 74BvsMistral Large 4Frequently asked questions
DeepSeek-V4-Pro leads Nemotron 3.5 Bolt 74B on 2 of the 2 benchmarks they both report (BrowseComp, GPQA Diamond). DeepSeek-V4-Pro shipped 174 days before Nemotron 3.5 Bolt 74B, 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 BrowseComp, DeepSeek-V4-Pro leads at 83.4% vs Nemotron 3.5 Bolt 74B at 66.75%. On GPQA Diamond, DeepSeek-V4-Pro leads at 90.1% vs Nemotron 3.5 Bolt 74B at 86.43%.