Open-weight Muse Spark posts eye-catching benchmark sweep, topping Kimi K3 and GLM 5.3 on several evals
Xianbao_QIAN · x · 2026-10-16
X user XianbaoQIAN shared benchmark results for a new open-weight model called Muse Spark. The chart shows Muse Spark (xhigh) leading on MCP-Atlas (89.2), JobBench (61.8), AA-Omniscience (25 vs 20 for Kimi K3), HLE-Diamond (26.1) and ZeroBench (50.0), plus multimodal scores (BabyVision 80.2) most rivals don't support. It trails on coding: Terminal-Bench 2.1 at 76.4 vs Kimi K3's 85.0, and GLM 5.3 tops GDPval-AA v2 at 1653. Compared models include Mistral Large 4, Qwen3.8-2.4T-A95B and Nemotron 3 Ultra. Provenance unverified in the post.
Related event: Meta Open-Sources Muse Spark Open: 816B-Parameter MoE with 1M Context(54 posts)→
More from Models
- Dev Builds Haunted Escape Room to Test Reflection AI's Beam, Solves It in 30 Seconds — wandb · 2026-10-16
- Claude Opus 5.5 fast mode exits preview: 2.5x faster at $8/$40 per million tokens — ClaudeDevs · 2026-10-16
- NVIDIA ships Nemotron 3.5 Bolt: 74B-A9B model in 24GB of memory — NVIDIAAI · 2026-10-16
- User's Opus 5.5 High Blender 3D experiment crashes their Mac with hilarious results — imjustnewatai · 2026-10-16
- Apollo Research: GLM-5.3 Spontaneously Reasons About How Its Actions Shape Future Training — jd_pressman · 2026-10-16
- Datalab's Chandra 2.5 hits API: 40% faster, more accurate, still $3 per 1,000 pages — VikParuchuri · 2026-10-16