Muse GlimmervsKimi K2 (0905)
Muse Glimmer | Kimi K2 (0905) | |
|---|---|---|
| Specifications | ||
Parameters | 30B | 1T |
Context window | — | 256k |
| 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. | 51.2% | — |
Coding SWE-Bench VerifiedReal 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. | 76%Best | 65.8% |
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. | 51.7% | — |
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. | 75.5% | — |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 22% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 83.5%Best | 75.1% |
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. | 65.9% | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | 953 | — |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | 78.8% | — |
Multimodal reasoning MMMU-ProA tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 74% | — |
| Overview | ||
| Company | Meta | Moonshot AI |
| Release date | Aug 10 2026 | Sep 5 2025 |
| Access | Open Weight | Open Weight |
Which is better: Muse Glimmer or Kimi K2 (0905)?
Muse Glimmer leads Kimi K2 (0905) on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). Kimi K2 (0905) shipped 339 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.
Muse Glimmer has 30B parameters, while Kimi K2 (0905) has 1T.
On SWE-Bench Verified, Muse Glimmer leads at 76% vs Kimi K2 (0905) at 65.8%. On GPQA Diamond, Muse Glimmer leads at 83.5% vs Kimi K2 (0905) at 75.1%.
Frequently asked questions
Muse Glimmer was released by Meta on Aug 10 2026.
Kimi K2 (0905) was released by Moonshot AI on Sep 5 2025.
Muse Glimmer leads on SWE-Bench Verified — Muse Glimmer 76% vs Kimi K2 (0905) 65.8%.
Muse Glimmer leads on GPQA Diamond — Muse Glimmer 83.5% vs Kimi K2 (0905) 75.1%.
Other comparisons
Muse GlimmervsClaude Opus 5Kimi K2 (0905)vsClaude Opus 5Muse GlimmervsGPT-5.6 SolKimi K2 (0905)vsGPT-5.6 SolMuse GlimmervsGemini 3.6 FlashKimi K2 (0905)vsGemini 3.6 FlashMuse GlimmervsGrok 4.5Kimi K2 (0905)vsGrok 4.5Muse GlimmervsDeepSeek-V4-Flash-0731Kimi K2 (0905)vsDeepSeek-V4-Flash-0731Muse GlimmervsMistral Medium 3.5Kimi K2 (0905)vsMistral Medium 3.5