Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 671B | 74B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 128k | 256k |
| 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. | $0.27SiliconFlow | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.00SiliconFlow | — |
| $104SiliconFlow · fp8 | — | |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 80.7% | 86.43% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 68.4% | — |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 57.8% | — |
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. | 74.9% | — |
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% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 66.75% |
| Overview | ||
| Company | DeepSeek | NVIDIA |
| Release date | Sep 22 2025 | Oct 15 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V3.1 TerminusvsClaude Haiku 5.5Nemotron 3.5 Bolt 74BvsClaude Haiku 5.5DeepSeek V3.1 TerminusvsGPT-6.1 SolNemotron 3.5 Bolt 74BvsGPT-6.1 SolDeepSeek V3.1 TerminusvsGemini 4 ArgonNemotron 3.5 Bolt 74BvsGemini 4 ArgonDeepSeek V3.1 TerminusvsMuse Spark OpenNemotron 3.5 Bolt 74BvsMuse Spark OpenDeepSeek V3.1 TerminusvsGrok 4.7Nemotron 3.5 Bolt 74BvsGrok 4.7DeepSeek V3.1 TerminusvsMistral Large 4Nemotron 3.5 Bolt 74BvsMistral Large 4Frequently asked questions
Nemotron 3.5 Bolt 74B leads DeepSeek V3.1 Terminus on 1 of the 1 benchmark they both report (GPQA Diamond). DeepSeek V3.1 Terminus shipped 388 days before Nemotron 3.5 Bolt 74B, so benchmark comparisons should account for the intervening progress.
DeepSeek V3.1 Terminus has 671B parameters, while Nemotron 3.5 Bolt 74B has 74B. Context windows are 128k (DeepSeek V3.1 Terminus) vs 256k (Nemotron 3.5 Bolt 74B).
On GPQA Diamond, Nemotron 3.5 Bolt 74B leads at 86.43% vs DeepSeek V3.1 Terminus at 80.7%.