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. | 128k | 128k |
| 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. | 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. | — | 75.7% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 75.2% |
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 | — | 57.9% |
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% | — |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | — | 81.9% |
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. | — | 90.9% |
| Overview | ||
| Company | SpaceXSI | Z.ai |
| Release date | Feb 17 2025 | Jun 5 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Grok 3 minivsClaude Fable 5.2GLM-4-AirvsClaude Fable 5.2Grok 3 minivsGPT-6.2 AstraGLM-4-AirvsGPT-6.2 AstraGrok 3 minivsGemini 4 HydrogenGLM-4-AirvsGemini 4 HydrogenGrok 3 minivsMuse EmberGLM-4-AirvsMuse EmberGrok 3 minivsDeepSeek-V4.1-Flash-1017GLM-4-AirvsDeepSeek-V4.1-Flash-1017Grok 3 minivsMistral Large 4GLM-4-AirvsMistral Large 4Frequently asked questions
Grok 3 mini and GLM-4-Air don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GLM-4-Air shipped 257 days before Grok 3 mini, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Grok 3 mini) vs 128k (GLM-4-Air).
Direct benchmark comparisons are unavailable — Grok 3 mini and GLM-4-Air don't publish scores on any of the same benchmarks.