Muse Spark 1.1vsGLM-5.2
Across 7 shared benchmarks, Muse Spark 1.1 leads overall: Muse Spark 1.1 wins 4, GLM-5.2 wins 3, with 0 ties and an average score difference of -0.44.
Muse Spark 1.1
Facebook AI研究实验室 · 2026-07-09 · Reasoning model
GLM-5.2
智谱AI · 2026-06-13 · Reasoning model
Muse Spark 1.14 wins(57%)(43%)3 winsGLM-5.2
Benchmark scores
Grouped by capability, sorted by largest gap within each. 7 shared benchmarks.
AI Agent - Tool Usage
Muse Spark 1.1 2/3| Benchmark | Muse Spark 1.1 | GLM-5.2 | Diff |
|---|---|---|---|
| Tool Decathlon | 75.601 / 10Thinking (With Tools) | 48.204 / 10Thinking (With Tools) | +27.40 |
| MCP-Atlas | 88.101 / 38Thinking (With Tools) | 76.8013 / 38Thinking (With Tools) | +11.30 |
| Terminal-Bench 2.1 | 8019 / 44Thinking (With Tools) | 8117 / 44Thinking High (With Tools) | -1 |
Coding and Software Engineer
GLM-5.2 2/3| Benchmark | Muse Spark 1.1 | GLM-5.2 | Diff |
|---|---|---|---|
| Text Arena (Coding) | 1,53612 / 35Normal (No Tools) | 1,5935 / 35最高（无工具） | -56.89 |
| DeepSWE | 53.3017 / 27Thinking (With Tools) | 4421 / 27Deep Thinking (With Tools) | +9.30 |
| SWE-Bench Pro - Public | 61.5011 / 57Thinking (With Tools) | 62.109 / 57Thinking (With Tools) | -0.60 |
General Knowledge
Muse Spark 1.1 1/1| Benchmark | Muse Spark 1.1 | GLM-5.2 | Diff |
|---|---|---|---|
| HLE | 62.104 / 181Thinking (With Tools) | 54.7015 / 181Thinking (With Tools) | +7.40 |
Specs
| Field | Muse Spark 1.1 | GLM-5.2 |
|---|---|---|
| Publisher | Facebook AI研究实验室 | 智谱AI |
| Release date | 2026-07-09 | 2026-06-13 |
| Model type | Reasoning model | Reasoning model |
| Architecture | Dense | MoE |
| Parameters | Not available | 753.33B |
| Context length | 1M | 1M |
| Max output | Not available | 128K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Muse Spark 1.1 | GLM-5.2 |
|---|---|---|
| Text input | Not public | $1.4 / 1M tokens |
| Text output | Not public | $4.4 / 1M tokens |
| Cache read | Not public | $0.26 / 1M tokens |
One or both models have incomplete public pricing.
Summary
- Muse Spark 1.1leads in:AI Agent - Tool Usage (2/3), General Knowledge (1/1)
- GLM-5.2leads in:Coding and Software Engineer (2/3)
On average across the 7 shared benchmarks, GLM-5.2 scores 0.44 higher.
Largest single-benchmark gap: Text Arena (Coding) — Muse Spark 1.1 1,536 vs GLM-5.2 1,593 (-56.89).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.