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. | 24B | 355B |
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 | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.60 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $2.20 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.11 |
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. | — | $0.60Z.AI |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $2.20Z.AI |
| — | $230Z.ai list price | |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 70.07% | 79.1% |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 8% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 64.2% |
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. | 70.88% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 86.14% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 77.34% | — |
| Overview | ||
| Company | Mistral | Z.ai |
| Release date | Sep 17 2025 | Jul 28 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Magistral Small 1.2vsClaude Fable 5.2GLM-4.5vsClaude Fable 5.2Magistral Small 1.2vsGPT-6.2 AstraGLM-4.5vsGPT-6.2 AstraMagistral Small 1.2vsGemini 4 HydrogenGLM-4.5vsGemini 4 HydrogenMagistral Small 1.2vsMuse EmberGLM-4.5vsMuse EmberMagistral Small 1.2vsGrok 4.7GLM-4.5vsGrok 4.7Magistral Small 1.2vsDeepSeek-V4.1-Flash-1017GLM-4.5vsDeepSeek-V4.1-Flash-1017Frequently asked questions
GLM-4.5 leads Magistral Small 1.2 on 1 of the 1 benchmark they both report (GPQA Diamond). Only GLM-4.5 has a verified first-party price for an available API: $0.60 per million input tokens and $2.20 per million output tokens. No currently available pay-as-you-go API rate is tracked for Magistral Small 1.2. GLM-4.5 shipped 51 days before Magistral Small 1.2, so benchmark comparisons should account for the intervening progress.
Magistral Small 1.2 has 24B parameters, while GLM-4.5 has 355B. Context windows are 128k (Magistral Small 1.2) vs 128k (GLM-4.5).
On GPQA Diamond, GLM-4.5 leads at 79.1% vs Magistral Small 1.2 at 70.07%.