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 |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.40Mistral | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $2.00Mistral | — |
| $180Mistral · zdr | — | |
| Benchmarks | ||
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. | 92.1% | 75.7% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 89.4% | 75.2% |
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. | 30.3% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 57.9% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 91% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 57.1% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 77.2% | — |
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% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 66.1% | — |
| Overview | ||
| Company | Mistral | Z.ai |
| Release date | May 7 2025 | Jun 5 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Mistral Medium 3vsClaude Fable 5.2GLM-4-AirvsClaude Fable 5.2Mistral Medium 3vsGPT-6.2 AstraGLM-4-AirvsGPT-6.2 AstraMistral Medium 3vsGemini 4 HydrogenGLM-4-AirvsGemini 4 HydrogenMistral Medium 3vsMuse EmberGLM-4-AirvsMuse EmberMistral Medium 3vsGrok 4.7GLM-4-AirvsGrok 4.7Mistral Medium 3vsDeepSeek-V4.1-Flash-1017GLM-4-AirvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Mistral Medium 3 leads GLM-4-Air on 2 of the 2 benchmarks they both report (HumanEval, IFEval). GLM-4-Air shipped 336 days before Mistral Medium 3, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Mistral Medium 3) vs 128k (GLM-4-Air).
On HumanEval, Mistral Medium 3 leads at 92.1% vs GLM-4-Air at 75.7%. On IFEval, Mistral Medium 3 leads at 89.4% vs GLM-4-Air at 75.2%.