Terminus-2 – GLM-4.7-Flash (Reasoning) vs. Terminus-2 – Qwen 3.8 27B (xhigh): geospatial agent comparison
Comparison between Terminus-2 – GLM-4.7-Flash (Reasoning) and Terminus-2 – Qwen 3.8 27B (xhigh) on the Geospatial Agent Index, each benchmark, cost, time and token use, from the same tasks, agent and limits. Methodology.
Side by side
| Metric | Terminus-2 – GLM-4.7-Flash (Reasoning) | Terminus-2 – Qwen 3.8 27B (xhigh) |
|---|---|---|
| Geospatial Agent Index | 43* | 62* |
| GeoAgentBench score | 36 | 60 |
| GeoBenchX score | 46 | No data |
| Earth-Bench score | 48 | 27 |
| GeoAnalystBench score | 42 | 100 |
| Raster and remote sensing score | 39 | 36 |
| Vector and overlay score | 36 | 78 |
| Networks and routing score | 20 | 67 |
| Climate and time series score | 54 | 43 |
| Spatial statistics and interpolation score | 46 | 62 |
| Mapping and cartography score | 58 | 100 |
| Recognising infeasible requests score | 36 | No data |
| Cost per task | $0.025 | $0.066 |
| Time per task | 9.5 min | 19.8 min |
| Tokens per attempt | 332k | 90k |
| Turns per attempt | 15.8 | 8.2 |
| Attempts decided | 143 | 101 |
| Input price per 1M tokens | $0.06 | $0.45 |
| Output price per 1M tokens | $0.40 | $3.20 |
| Context window | 131,072 | 262,144 |
| Image input | No | Yes |
| Developer | Z.ai | Alibaba (Qwen) |
Charts
Axis Spatial Geospatial Agent Index
Equal-weight average of the evaluation scores, 0 to 100 · Higher is better
Data table: Axis Spatial Geospatial Agent Index
| Model | Creator | Geospatial Agent Index | Range while attempts are pending | Benchmarks covered | Coverage (attempts) |
|---|---|---|---|---|---|
| Terminus-2 – GLM-4.7-Flash (Reasoning) | Z.ai | 43* | 43 to 44 | 4 of 4 | 143 of 870 planned attempts |
| Terminus-2 – Qwen 3.8 27B (xhigh) | Alibaba (Qwen) | 62* | No pending judgements; coverage incomplete | 3 of 4 | 101 of 870 planned attempts |
Cost per task
Average cost per task (USD) · Lower is better
Data table: Cost per task
| Model | Creator | Cost per task | Coverage (attempts) |
|---|---|---|---|
| Terminus-2 – GLM-4.7-Flash (Reasoning) | Z.ai | $0.025 | 144 of 870 planned attempts |
| Terminus-2 – Qwen 3.8 27B (xhigh) | Alibaba (Qwen) | $0.066 | 101 of 870 planned attempts |
Time per task
Average agent wall time per task · Lower is better
Data table: Time per task
| Model | Creator | Time per task | Coverage (attempts) |
|---|---|---|---|
| Terminus-2 – GLM-4.7-Flash (Reasoning) | Z.ai | 9.5 min | 144 of 870 planned attempts |
| Terminus-2 – Qwen 3.8 27B (xhigh) | Alibaba (Qwen) | 19.8 min | 101 of 870 planned attempts |
Frequently asked questions
- Which scores higher on the Geospatial Agent Index, Terminus-2 – GLM-4.7-Flash (Reasoning) or Terminus-2 – Qwen 3.8 27B (xhigh)?
- Not comparable yet: Terminus-2 – Qwen 3.8 27B (xhigh) has scores on 3 of 4 benchmarks, so it is not yet ranked. Terminus-2 – GLM-4.7-Flash (Reasoning): 143 of 870 planned attempts. Terminus-2 – Qwen 3.8 27B (xhigh): 101 of 870 planned attempts. Coverage is partial; scores can change as more attempts are decided.
- Which is cheaper per task, Terminus-2 – GLM-4.7-Flash (Reasoning) or Terminus-2 – Qwen 3.8 27B (xhigh)?
- Terminus-2 – GLM-4.7-Flash (Reasoning), at $0.025 against $0.066 for Terminus-2 – Qwen 3.8 27B (xhigh).
- Which is faster per task, Terminus-2 – GLM-4.7-Flash (Reasoning) or Terminus-2 – Qwen 3.8 27B (xhigh)?
- Terminus-2 – GLM-4.7-Flash (Reasoning), at 9.5 min against 19.8 min for Terminus-2 – Qwen 3.8 27B (xhigh).
- Which has the larger context window, Terminus-2 – GLM-4.7-Flash (Reasoning) or Terminus-2 – Qwen 3.8 27B (xhigh)?
- Terminus-2 – Qwen 3.8 27B (xhigh), at 262,144 tokens against 131,072 tokens for Terminus-2 – GLM-4.7-Flash (Reasoning).
More: Terminus-2 – GLM-4.7-Flash (Reasoning) · Terminus-2 – Qwen 3.8 27B (xhigh) · all comparisons