GLM-5.2 (Non-reasoning) vs Muse Glimmer 30B (high)
Results updated 6 November 2026 · Both in Terminus-2 · How we benchmark
Verdict
Muse Glimmer 30B (high) edges GLM-5.2 (Non-reasoning) by 1 point, and is cheaper; GLM-5.2 (Non-reasoning) is faster.
- Cost per task
- $0.099 vs $0.078
- Time per task
- 1.5 min vs 3.0 min
- Tokens per attempt
- 185k vs 343k
- Image input
- No vs Yes
GLM-5.2 (Non-reasoning), Terminus-2 scores higher on GS-QA2; Muse Glimmer 30B (high), Terminus-2 scores higher on Earth-Bench V2 and GeoBenchX. Muse Glimmer 30B (high), Terminus-2 is cheaper ($0.078 against $0.099 per task), but GLM-5.2 (Non-reasoning), Terminus-2 is faster (1.5 min against 3.0 min).
Where they differ most
By kind of work, share of tasks passed, 0 to 100 · Higher is better
| Kind of work | GLM-5.2 (Non-reasoning) | Muse Glimmer 30B (high) |
|---|---|---|
| Spatial statistics | 31 | 8 |
| Recognising infeasible requests | 45 | 67 |
| Remote sensing and raster analysis | 72 | 63 |
| Making maps | 79 | 75 |
Where the tasks are set: each kind of work links to its tasks and scoresCharts for each: GLM-5.2 (Non-reasoning), Terminus-2 · Muse Glimmer 30B (high), Terminus-2.
Side by side
| Metric | GLM-5.2 (Non-reasoning), Terminus-2 | Muse Glimmer 30B (high), Terminus-2 |
|---|---|---|
| Geospatial Agent Index: Text only | 63 | 64 |
| Geospatial Agent Index: Text + vision | No image input | No data |
| Earth-Bench V2 score | 58 | 60 |
| GeoBenchX score | 60 | 61 |
| GS-QA2 score | 72 | 70 |
| Vision agents score | No image input | No data |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 92 | 79 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 74 | 58 |
| OGD4All score (standalone; in no index) | No data | 95 |
| GeoNatureAgent score (standalone; in no index) | No data | 100 |
| MultiGlobeQA score (standalone; in no index) | No data | 72 |
| GeoAgentEval score (standalone; in no index) | No data | 92 |
| ImpactMesh score (standalone; in no index) | No data | No data |
| Remote sensing and raster analysis score | 72 | 63 |
| GIS analysis score | 65 | 69 |
| Climate and time series score | 58 | 61 |
| Spatial statistics score | 31 | 8 |
| Making maps score | 79 | 75 |
| Recognising infeasible requests score | 45 | 67 |
| Cost per task | $0.099 | $0.078 |
| Time per task (at 100 output tokens/s) | 1.5 min | 3.0 min |
| Tokens per attempt | 185k | 343k |
| Turns per attempt | 12.8 | 25.3 |
| Input price per 1M tokens | $1.40 | $0.35 |
| Output price per 1M tokens | $4.40 | $1.50 |
| Context window | 262,144 | 131,072 |
| Image input | No | Yes |
| Developer | Z.ai | Meta |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, GLM-5.2 (Non-reasoning), Terminus-2 or Muse Glimmer 30B (high), Terminus-2?
Muse Glimmer 30B (high), Terminus-2, 64 to 63.
Which is cheaper per task, GLM-5.2 (Non-reasoning), Terminus-2 or Muse Glimmer 30B (high), Terminus-2?
Muse Glimmer 30B (high), Terminus-2, $0.078 to $0.099.
Which writes fewer output tokens per task, GLM-5.2 (Non-reasoning), Terminus-2 or Muse Glimmer 30B (high), Terminus-2?
GLM-5.2 (Non-reasoning), Terminus-2, 6k to 11k.
Which has the larger context window, GLM-5.2 (Non-reasoning), Terminus-2 or Muse Glimmer 30B (high), Terminus-2?
GLM-5.2 (Non-reasoning), Terminus-2, 262,144 tokens to 131,072 tokens.