Llama Nemotron Ultra 253BvsGLM-5.2
Llama Nemotron Ultra 253B | GLM-5.2 | |
|---|---|---|
| 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. | 253B | 744B |
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. | — | 1M |
| 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. | — | $1.40 |
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. | — | $4.40 |
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. | — | $0.26 |
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. | — | $0.50Sail Research |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $2.00Ambient |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 76% | 91.2% |
| BenchmarksPublished by one model only | ||
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. | — | 31% |
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | — | 62.1% |
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | — | 44% |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | — | 88% |
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. | 66.3% | — |
Frontier-Bench v0.1Agentic computer work — A hard, ever-evolving set of real computer tasks — coding, system administration, data work, and more — that an AI agent has to complete on its own. Run by the Harbor / Laude Institute team as the successor to Terminal-Bench (v0.1 is the first release of the task set). The score is the share of tasks solved. Higher is better. | — | 5.1% |
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. | — | 81% |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 40.5% |
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. | — | 54.7% |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | — | 1514 |
| Overview | ||
| Company | NVIDIA | Z.ai |
| Release date | Apr 8 2025 | Jun 16 2026 |
| Access | Open Weight | Open Weight |
Other comparisons
Llama Nemotron Ultra 253BvsClaude Opus 5GLM-5.2vsClaude Opus 5Llama Nemotron Ultra 253BvsGPT-5.6 SolGLM-5.2vsGPT-5.6 SolLlama Nemotron Ultra 253BvsGemini 3.7 FlashGLM-5.2vsGemini 3.7 FlashLlama Nemotron Ultra 253BvsMuse GlimmerGLM-5.2vsMuse GlimmerLlama Nemotron Ultra 253BvsGrok 4.6GLM-5.2vsGrok 4.6Llama Nemotron Ultra 253BvsDeepSeek-V4-Pro-0813GLM-5.2vsDeepSeek-V4-Pro-0813
Frequently asked questions
GLM-5.2 leads Llama Nemotron Ultra 253B on 1 of the 1 benchmark they both report (GPQA Diamond). Only GLM-5.2 has a verified first-party API price: $1.40 per million input tokens and $4.40 per million output tokens. No pay-as-you-go API rate is tracked for Llama Nemotron Ultra 253B. Llama Nemotron Ultra 253B shipped 434 days before GLM-5.2, so benchmark comparisons should account for the intervening progress.
Llama Nemotron Ultra 253B has 253B parameters, while GLM-5.2 has 744B.
On GPQA Diamond, GLM-5.2 leads at 91.2% vs Llama Nemotron Ultra 253B at 76%.
Llama Nemotron Ultra 253B was released by NVIDIA on Apr 8 2025.
GLM-5.2 was released by Z.ai on Jun 16 2026.
GLM-5.2 leads on GPQA Diamond — Llama Nemotron Ultra 253B 76% vs GLM-5.2 91.2%.
Only GLM-5.2 has a verified first-party API price: $1.40 per million input tokens and $4.40 per million output tokens. No pay-as-you-go API rate is tracked for Llama Nemotron Ultra 253B. Rates are pay-as-you-go API prices verified on August 18, 2026.