Devstral 2 (123B)vsGLM-5.3-Flash
Devstral 2 (123B) | GLM-5.3-Flash | |
|---|---|---|
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | — | 320B |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | — | 1M |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.40Mistral | $0.075DeepInfra |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $2.00Mistral | $0.25DeepInfra |
| BenchmarksPublished by one model only | ||
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | — | 63.4% |
NL2Repo-BenchRepo-level code generation — Tests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. | — | 56.3% |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 84.3% |
Toolathlon-VerifiedPersonal tool use — Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | — | 78.4% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 55.3% |
Agent's Last Exam · pass@1Agentic computer use — A hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better. | — | 26.3% |
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | — | 48.8% |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | — | 1773 |
CharXiv Reasoning · with toolsChart reasoning — The same chart-and-figure reasoning test, run with the AI allowed to use tools — writing code to inspect the image, for instance — rather than reading the chart unaided. Scores run higher than the unaided version, so read the two as separate tests. Higher is better. | — | 89.4% |
Chartography · with toolsChart tasks — A chart-centred test run with tools available to the AI, reported separately from the chart-reading benchmarks above it. Higher is better. | — | 78% |
OfficeQA ProDocument Q&A — Questions about office documents, where answering depends on reading the page as a document — layout, tables and figures included — rather than as loose text. Higher is better. | — | 62.4% |
MVBenchVideo understanding — Video questions that cannot be answered from any single frame: the AI has to follow what changes over time — the order things happen in, what moved where. Higher is better. | — | 77.8% |
MMVUVideo reasoning — Expert-level video questions drawn from specific disciplines, where answering means applying subject knowledge to what is happening on screen rather than just describing it. Higher is better. | — | 80.5% |
BabyVisionVisual reasoning — Tests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better. | — | 53.4% |
| Overview | ||
| Company | Mistral | Z.ai |
| Release date | Dec 9 2025 | Aug 26 2026 |
| Access | Open Weight | Open Weight |
Other comparisons
Devstral 2 (123B)vsClaude Fable 5.1GLM-5.3-FlashvsClaude Fable 5.1Devstral 2 (123B)vsGPT-6 AstraGLM-5.3-FlashvsGPT-6 AstraDevstral 2 (123B)vsGemini 3.8 FlashGLM-5.3-FlashvsGemini 3.8 FlashDevstral 2 (123B)vsMuse Spark 1.3GLM-5.3-FlashvsMuse Spark 1.3Devstral 2 (123B)vsGrok 4.6GLM-5.3-FlashvsGrok 4.6Devstral 2 (123B)vsDeepSeek-V4-Pro-0813GLM-5.3-FlashvsDeepSeek-V4-Pro-0813
Frequently asked questions
Devstral 2 (123B) and GLM-5.3-Flash don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Devstral 2 (123B) shipped 260 days before GLM-5.3-Flash, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
Direct benchmark comparisons are unavailable — Devstral 2 (123B) and GLM-5.3-Flash don't publish scores on any of the same benchmarks.
Devstral 2 (123B) was released by Mistral on Dec 9 2025.
GLM-5.3-Flash was released by Z.ai on Aug 26 2026.