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 | 9B/32B |
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 | 128k |
| 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% | 59.1% |
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. | 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. | 60.5% | — |
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% | — |
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 | — | 84.5% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 31.28% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 80.8% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 63.6% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 79.2% | — |
AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals | 36 | — |
| Overview | ||
| Company | NVIDIA | Z.ai |
| Release date | Mar 11 2026 | Apr 14 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Nemotron 3 SupervsClaude Fable 5.2GLM-Z1-0414vsClaude Fable 5.2Nemotron 3 SupervsGPT-6.2 AstraGLM-Z1-0414vsGPT-6.2 AstraNemotron 3 SupervsGemini 4 HydrogenGLM-Z1-0414vsGemini 4 HydrogenNemotron 3 SupervsMuse EmberGLM-Z1-0414vsMuse EmberNemotron 3 SupervsGrok 4.7GLM-Z1-0414vsGrok 4.7Nemotron 3 SupervsDeepSeek-V4.1-Flash-1017GLM-Z1-0414vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Nemotron 3 Super leads GLM-Z1-0414 on 1 of the 1 benchmark they both report (LiveCodeBench). GLM-Z1-0414 shipped 331 days before Nemotron 3 Super, so benchmark comparisons should account for the intervening progress.
Nemotron 3 Super has 120B parameters, while GLM-Z1-0414 has 9B/32B. Context windows are 1M (Nemotron 3 Super) vs 128k (GLM-Z1-0414).
On LiveCodeBench, Nemotron 3 Super leads at 81.19% vs GLM-Z1-0414 at 59.1%.