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. | 120B | — |
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 | 1M |
| 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. | $0.06DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.32DeepInfra | — |
| $35.00DeepInfra · bf16 | — | |
| Benchmarks | ||
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. | 81.19% | 37.8% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 83.73% | 64.5% |
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. | 54% | — |
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. | 60.47% | — |
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. | 45.78% | — |
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. | — | 86.6% |
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. | 39.61% | — |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | 31% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 76.3% |
τ²-bench · retailAgentic tasks — task success in the retail domain of the second-generation customer-service evaluation | 62.83% | — |
τ²-bench · airlineAgentic tasks — task success in the airline domain of the second-generation customer-service evaluation | 56.25% | — |
τ²-bench · telecomAgentic tasks — task success in the telecom domain of the second-generation customer-service evaluation | 64.36% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 31.28% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 20.3% | — |
Humanity's Last Exam · text only, with toolsMultidisciplinary reasoning — The text-only questions from Humanity's Last Exam, answered with access to tools such as search or code execution. The score is the percentage answered correctly. | 22.82% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 81.1% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 90.21% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 79.23% | — |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | — | 93.8% |
AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals | 36 | — |
| Overview | ||
| Company | NVIDIA | Qwen |
| Release date | Mar 11 2026 | Nov 15 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Nemotron 3 SupervsClaude Fable 5.2Qwen2.5-Turbo (1M)vsClaude Fable 5.2Nemotron 3 SupervsGPT-6.2 AstraQwen2.5-Turbo (1M)vsGPT-6.2 AstraNemotron 3 SupervsGemini 4 NeonQwen2.5-Turbo (1M)vsGemini 4 NeonNemotron 3 SupervsMuse EmberQwen2.5-Turbo (1M)vsMuse EmberNemotron 3 SupervsGrok 4.7Qwen2.5-Turbo (1M)vsGrok 4.7Nemotron 3 SupervsDeepSeek-V4.1-Flash-1017Qwen2.5-Turbo (1M)vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Nemotron 3 Super leads Qwen2.5-Turbo (1M) on 2 of the 2 benchmarks they both report (LiveCodeBench, MMLU-Pro). Qwen2.5-Turbo (1M) shipped 481 days before Nemotron 3 Super, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Nemotron 3 Super) vs 1M (Qwen2.5-Turbo (1M)). Nemotron 3 Super is open weight, while Qwen2.5-Turbo (1M) is closed.
On LiveCodeBench, Nemotron 3 Super leads at 81.19% vs Qwen2.5-Turbo (1M) at 37.8%. On MMLU-Pro, Nemotron 3 Super leads at 83.73% vs Qwen2.5-Turbo (1M) at 64.5%.