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. | 550B | 32B |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | — | 128k |
| 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. | $0.50DeepInfra | $0.66Cloudflare |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $2.20DeepInfra | $1.00Cloudflare |
These models have no shared benchmark scores. | ||
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. | 49% | — |
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. | 71.9% | — |
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. | 56.4% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 44.4% | — |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | 26.7% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 86.7% | — |
AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals | 48 | — |
| Overview | ||
| Company | NVIDIA | Qwen |
| Release date | Jun 4 2026 | Nov 12 2024 |
| Access | Open Source | Open Weight |
| Model details | View model | View model |
Other comparisons
Nemotron 3 UltravsClaude Haiku 5.5Qwen2.5-CodervsClaude Haiku 5.5Nemotron 3 UltravsGPT-6.1 SolQwen2.5-CodervsGPT-6.1 SolNemotron 3 UltravsGemini 4 ArgonQwen2.5-CodervsGemini 4 ArgonNemotron 3 UltravsMuse Spark 1.3Qwen2.5-CodervsMuse Spark 1.3Nemotron 3 UltravsGrok 4.7Qwen2.5-CodervsGrok 4.7Nemotron 3 UltravsDeepSeek-V4.1-FlashQwen2.5-CodervsDeepSeek-V4.1-FlashFrequently asked questions
Nemotron 3 Ultra and Qwen2.5-Coder don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Coder shipped 569 days before Nemotron 3 Ultra, so benchmark comparisons should account for the intervening progress.
Nemotron 3 Ultra has 550B parameters, while Qwen2.5-Coder has 32B. Nemotron 3 Ultra is open source, while Qwen2.5-Coder is open weight.
Direct benchmark comparisons are unavailable — Nemotron 3 Ultra and Qwen2.5-Coder don't publish scores on any of the same benchmarks.