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. | 123B | 9B/32B |
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. | 256k | 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 | — | |
| These models have no shared benchmark scores. | ||
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. | 72.2% | — |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 61.3% | — |
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. | — | 59.1% |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | 32.6% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 84.5% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 80.8% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 63.6% |
| Overview | ||
| Company | Mistral | Z.ai |
| Release date | Dec 9 2025 | Apr 14 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Devstral 2 (123B)vsClaude Fable 5.2GLM-Z1-0414vsClaude Fable 5.2Devstral 2 (123B)vsGPT-6.2 AstraGLM-Z1-0414vsGPT-6.2 AstraDevstral 2 (123B)vsGemini 4 HydrogenGLM-Z1-0414vsGemini 4 HydrogenDevstral 2 (123B)vsMuse EmberGLM-Z1-0414vsMuse EmberDevstral 2 (123B)vsGrok 4.7GLM-Z1-0414vsGrok 4.7Devstral 2 (123B)vsDeepSeek-V4.1-Flash-1017GLM-Z1-0414vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Devstral 2 (123B) and GLM-Z1-0414 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GLM-Z1-0414 shipped 239 days before Devstral 2 (123B), so benchmark comparisons should account for the intervening progress.
Devstral 2 (123B) has 123B parameters, while GLM-Z1-0414 has 9B/32B. Context windows are 256k (Devstral 2 (123B)) vs 128k (GLM-Z1-0414).
Direct benchmark comparisons are unavailable — Devstral 2 (123B) and GLM-Z1-0414 don't publish scores on any of the same benchmarks.