Muse Spark 1.1 vs Devstral Small 2 (24B)
Meta Muse Spark 1.1 | Mistral Devstral Small 2 (24B) | |
|---|---|---|
| Overview | ||
| Company | Meta | Mistral |
| Release date | Jul 9 2026 | Dec 9 2025 |
| Access | Proprietary | Open Weight |
| Benchmarks | ||
Agentic coding SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 61.5% | — |
Agentic coding DeepSWE 1.1Artificial 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. | 53.3% | — |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 80% | — |
Multi-step tool use MCP AtlasCan the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | 88.1% | — |
Professional tool use JobBenchTests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | 54.7% | — |
Personal tool use Toolathlon-VerifiedTests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | 75.6% | — |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity'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. | 62.1% | — |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 80.8% | — |
Agentic financial analysis Finance Agent v2Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | 57.2% | — |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | 88.4% | — |
Visual reasoning BabyVisionTests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better. | 76.3% | — |
| Timeline | ||
| Release gap | Devstral Small 2 (24B) shipped 212 days before Muse Spark 1.1 | |
Which is better: Muse Spark 1.1 or Devstral Small 2 (24B)?
Muse Spark 1.1 and Devstral Small 2 (24B) don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Devstral Small 2 (24B) shipped 212 days before Muse Spark 1.1, so benchmark comparisons should account for the intervening progress.
Muse Spark 1.1 is proprietary, while Devstral Small 2 (24B) is open weight.
Direct benchmark comparisons are unavailable — Muse Spark 1.1 and Devstral Small 2 (24B) don't publish scores on any of the same benchmarks.
Frequently asked questions
Muse Spark 1.1 was released by Meta on Jul 9 2026.
Devstral Small 2 (24B) was released by Mistral on Dec 9 2025.
Muse Spark 1.1 is a proprietary model released by Meta. Devstral Small 2 (24B) is an open weight model released by Mistral.
Other comparisons
Muse Spark 1.1 vs Claude Sonnet 5Devstral Small 2 (24B) vs Claude Sonnet 5Muse Spark 1.1 vs GPT-5.6 SolDevstral Small 2 (24B) vs GPT-5.6 SolMuse Spark 1.1 vs Gemini OmniDevstral Small 2 (24B) vs Gemini OmniMuse Spark 1.1 vs Grok 4.5Devstral Small 2 (24B) vs Grok 4.5Muse Spark 1.1 vs DeepSeek-V4-ProDevstral Small 2 (24B) vs DeepSeek-V4-ProMuse Spark 1.1 vs Kimi K2.7 CodeDevstral Small 2 (24B) vs Kimi K2.7 Code