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. | 74B | 7B/14B |
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. | 256k | 1M |
| These models have no shared benchmark scores. | ||
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. | — | 38.6% |
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. | — | 88.4% |
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. | 50.98% | — |
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | 52.2% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 84.3% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 66.75% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 79.5% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 86.43% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 63.3% |
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. | — | 94.8% |
| Overview | ||
| Company | NVIDIA | Qwen |
| Release date | Oct 15 2026 | Jan 27 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Nemotron 3.5 Bolt 74BvsClaude Fable 5.2Qwen2.5-1MvsClaude Fable 5.2Nemotron 3.5 Bolt 74BvsGPT-6.2 AstraQwen2.5-1MvsGPT-6.2 AstraNemotron 3.5 Bolt 74BvsGemini 4 NeonQwen2.5-1MvsGemini 4 NeonNemotron 3.5 Bolt 74BvsMuse EmberQwen2.5-1MvsMuse EmberNemotron 3.5 Bolt 74BvsGrok 4.7Qwen2.5-1MvsGrok 4.7Nemotron 3.5 Bolt 74BvsDeepSeek-V4.1-Flash-1017Qwen2.5-1MvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Nemotron 3.5 Bolt 74B and Qwen2.5-1M don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-1M shipped 626 days before Nemotron 3.5 Bolt 74B, so benchmark comparisons should account for the intervening progress.
Nemotron 3.5 Bolt 74B has 74B parameters, while Qwen2.5-1M has 7B/14B. Context windows are 256k (Nemotron 3.5 Bolt 74B) vs 1M (Qwen2.5-1M).
Direct benchmark comparisons are unavailable — Nemotron 3.5 Bolt 74B and Qwen2.5-1M don't publish scores on any of the same benchmarks.