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. | 30B | 7B |
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. | 1M | 64k |
| 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. | $0.00Nvidia | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.00Nvidia | — |
| $11.00Darkbloom · int4 | — | |
| These models have no shared benchmark scores. | ||
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. | 51.56% | — |
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. | 39.33% | — |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | — | 83.5% |
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. | 24.58% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 36.97% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 11.72% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 75.44% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 81.94% | — |
| Overview | ||
| Company | NVIDIA | Qwen |
| Release date | Aug 11 2026 | Apr 16 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Nemotron 3.5 LightningvsClaude Fable 5.2CodeQwen1.5vsClaude Fable 5.2Nemotron 3.5 LightningvsGPT-6.2 AstraCodeQwen1.5vsGPT-6.2 AstraNemotron 3.5 LightningvsGemini 4 NeonCodeQwen1.5vsGemini 4 NeonNemotron 3.5 LightningvsMuse EmberCodeQwen1.5vsMuse EmberNemotron 3.5 LightningvsGrok 4.7CodeQwen1.5vsGrok 4.7Nemotron 3.5 LightningvsDeepSeek-V4.1-Flash-1017CodeQwen1.5vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Nemotron 3.5 Lightning and CodeQwen1.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. CodeQwen1.5 shipped 847 days before Nemotron 3.5 Lightning, so benchmark comparisons should account for the intervening progress.
Nemotron 3.5 Lightning has 30B parameters, while CodeQwen1.5 has 7B. Context windows are 1M (Nemotron 3.5 Lightning) vs 64k (CodeQwen1.5).
Direct benchmark comparisons are unavailable — Nemotron 3.5 Lightning and CodeQwen1.5 don't publish scores on any of the same benchmarks.