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. | 1.5B/7B/72B | — |
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. | 4k | 2M |
| 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. | — | 80% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 44.9% |
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. | — | 20% |
MATHReasoning — accuracy on the original competition mathematics test set | 85.9% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 92% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 85.7% |
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. | 95.9% | — |
| Overview | ||
| Company | Qwen | SpaceXSI |
| Release date | Sep 19 2024 | Sep 19 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Qwen2.5-MathvsClaude Fable 5.2Grok 4 FastvsClaude Fable 5.2Qwen2.5-MathvsGPT-6.2 AstraGrok 4 FastvsGPT-6.2 AstraQwen2.5-MathvsGemini 4 NeonGrok 4 FastvsGemini 4 NeonQwen2.5-MathvsMuse EmberGrok 4 FastvsMuse EmberQwen2.5-MathvsDeepSeek-V4.1-Flash-1017Grok 4 FastvsDeepSeek-V4.1-Flash-1017Qwen2.5-MathvsMistral Large 4Grok 4 FastvsMistral Large 4Frequently asked questions
Qwen2.5-Math and Grok 4 Fast don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Math shipped 365 days before Grok 4 Fast, so benchmark comparisons should account for the intervening progress.
Context windows are 4k (Qwen2.5-Math) vs 2M (Grok 4 Fast). Qwen2.5-Math is open weight, while Grok 4 Fast is closed.
Direct benchmark comparisons are unavailable — Qwen2.5-Math and Grok 4 Fast don't publish scores on any of the same benchmarks.