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. | 51B | 355B |
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 | 200k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.60 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $2.20 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.11 |
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. | — | $0.40DeepInfra |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $1.60DeepInfra |
| — | $174Venice · fp4 | |
| 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. | — | 68% |
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. | — | 53.8% |
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. | — | 82.8% |
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. | — | 24.5% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 45.1% |
ARC-ChallengeReasoning — multiple-choice science questions from the AI2 Reasoning Challenge; unrelated to ARC-AGI | 69.2% | — |
HellaSwagReasoning — commonsense completion of short scenarios | 85.58% | — |
WinoGrandeReasoning — resolving ambiguous pronouns in context | 84.53% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 93.9% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 81% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 83.2% |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 80.2% | — |
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. | 91.43% | — |
| Overview | ||
| Company | NVIDIA | Z.ai |
| Release date | Sep 23 2024 | Sep 30 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Llama 3.1 Nemotron 51BvsClaude Fable 5.2GLM-4.6vsClaude Fable 5.2Llama 3.1 Nemotron 51BvsGPT-6.2 AstraGLM-4.6vsGPT-6.2 AstraLlama 3.1 Nemotron 51BvsGemini 4 NeonGLM-4.6vsGemini 4 NeonLlama 3.1 Nemotron 51BvsMuse EmberGLM-4.6vsMuse EmberLlama 3.1 Nemotron 51BvsGrok 4.7GLM-4.6vsGrok 4.7Llama 3.1 Nemotron 51BvsDeepSeek-V4.1-Flash-1017GLM-4.6vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Llama 3.1 Nemotron 51B and GLM-4.6 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only GLM-4.6 has a verified first-party price for an available API: $0.60 per million input tokens and $2.20 per million output tokens. No currently available pay-as-you-go API rate is tracked for Llama 3.1 Nemotron 51B. Llama 3.1 Nemotron 51B shipped 372 days before GLM-4.6, so benchmark comparisons should account for the intervening progress.
Llama 3.1 Nemotron 51B has 51B parameters, while GLM-4.6 has 355B. Context windows are 128k (Llama 3.1 Nemotron 51B) vs 200k (GLM-4.6).
Direct benchmark comparisons are unavailable — Llama 3.1 Nemotron 51B and GLM-4.6 don't publish scores on any of the same benchmarks.