Compare AI models
| Specifications | ||
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. | 1M | 128k |
| Benchmarks | ||
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. | 37.8% | 74.8% |
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. | 86.6% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 76.3% | — |
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. | — | 11% |
MATHReasoning — accuracy on the original competition mathematics test set | 81.1% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 83% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 79% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 64.5% | — |
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. | 93.8% | — |
| Overview | ||
| Company | Qwen | SpaceXSI |
| Release date | Nov 15 2024 | Feb 17 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Qwen2.5-Turbo (1M)vsClaude Fable 5.2Grok 3 minivsClaude Fable 5.2Qwen2.5-Turbo (1M)vsGPT-6.2 AstraGrok 3 minivsGPT-6.2 AstraQwen2.5-Turbo (1M)vsGemini 4 NeonGrok 3 minivsGemini 4 NeonQwen2.5-Turbo (1M)vsMuse EmberGrok 3 minivsMuse EmberQwen2.5-Turbo (1M)vsDeepSeek-V4.1-Flash-1017Grok 3 minivsDeepSeek-V4.1-Flash-1017Qwen2.5-Turbo (1M)vsMistral Large 4Grok 3 minivsMistral Large 4Frequently asked questions
Grok 3 mini leads Qwen2.5-Turbo (1M) on 1 of the 1 benchmark they both report (LiveCodeBench). Qwen2.5-Turbo (1M) shipped 94 days before Grok 3 mini, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Qwen2.5-Turbo (1M)) vs 128k (Grok 3 mini).
On LiveCodeBench, Grok 3 mini leads at 74.8% vs Qwen2.5-Turbo (1M) at 37.8%.