Gemini 3.0 ProvsLlama Nemotron Ultra 253B
Gemini 3.0 Pro | Llama Nemotron Ultra 253B | |
|---|---|---|
| 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 |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.9% | 76% |
| BenchmarksPublished by one model only | ||
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. | 76.2% | — |
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. | 67% | — |
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% |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 31.1% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 81% | — |
| Overview | ||
| Company | NVIDIA | |
| Release date | Nov 18 2025 | Apr 8 2025 |
| Access | Proprietary | Open Weight |
Other comparisons
Gemini 3.0 ProvsClaude Opus 5Llama Nemotron Ultra 253BvsClaude Opus 5Gemini 3.0 ProvsGPT-5.6 SolLlama Nemotron Ultra 253BvsGPT-5.6 SolGemini 3.0 ProvsMuse GlimmerLlama Nemotron Ultra 253BvsMuse GlimmerGemini 3.0 ProvsGrok 4.6Llama Nemotron Ultra 253BvsGrok 4.6Gemini 3.0 ProvsDeepSeek-V4-Pro-0813Llama Nemotron Ultra 253BvsDeepSeek-V4-Pro-0813Gemini 3.0 ProvsMistral Medium 3.5Llama Nemotron Ultra 253BvsMistral Medium 3.5
Frequently asked questions
Gemini 3.0 Pro leads Llama Nemotron Ultra 253B on 1 of the 1 benchmark they both report (GPQA Diamond). Llama Nemotron Ultra 253B shipped 224 days before Gemini 3.0 Pro, so benchmark comparisons should account for the intervening progress.
Gemini 3.0 Pro is proprietary, while Llama Nemotron Ultra 253B is open weight.
On GPQA Diamond, Gemini 3.0 Pro leads at 91.9% vs Llama Nemotron Ultra 253B at 76%.
Gemini 3.0 Pro was released by Google on Nov 18 2025.
Llama Nemotron Ultra 253B was released by NVIDIA on Apr 8 2025.
Gemini 3.0 Pro leads on GPQA Diamond — Gemini 3.0 Pro 91.9% vs Llama Nemotron Ultra 253B 76%.
Gemini 3.0 Pro is a proprietary model released by Google. Llama Nemotron Ultra 253B is an open weight model released by NVIDIA.