Terminus-2 – DeepSeek V4 Pro (high) vs. Terminus-2 – GLM-4.7-Flash (thinking on): geospatial agent comparison
Comparison between Terminus-2 – DeepSeek V4 Pro (high) and Terminus-2 – GLM-4.7-Flash (thinking on) 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 – DeepSeek V4 Pro (high) | Terminus-2 – GLM-4.7-Flash (thinking on) |
|---|---|---|
| Geospatial Agent Index | 73* | 41* |
| GeoAgentBench score | 98 | 36 |
| GeoBenchX score | 46 | 39 |
| Earth-Bench score | 48 | 45 |
| GeoAnalystBench score | 100 | 42 |
| Raster and remote sensing score | 74 | 36 |
| Vector and overlay score | 71 | 36 |
| Networks and routing score | 100 | 20 |
| Climate and time series score | 65 | 55 |
| Spatial statistics and interpolation score | 53 | 40 |
| Mapping and cartography score | 69 | 54 |
| Recognising infeasible requests score | 42 | 36 |
| Cost per task | $0.265 | $0.027 |
| Time per task | 8.6 min | 10.0 min |
| Tokens per attempt | 201k | 357k |
| Turns per attempt | 12.8 | 16.6 |
| Attempts decided | 209 | 176 |
| Input price per 1M tokens | $1.32 | $0.06 |
| Output price per 1M tokens | $3.96 | $0.40 |
| Context window | 1,048,576 | 131,072 |
| Image input | No | No |
| Developer | DeepSeek | Z.ai |
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 – DeepSeek V4 Pro (high) | DeepSeek | 73* | No pending judgements; coverage incomplete | 4 of 4 | 209 of 870 planned attempts |
| Terminus-2 – GLM-4.7-Flash (thinking on) | Z.ai | 41* | No pending judgements; coverage incomplete | 4 of 4 | 176 of 870 planned attempts |
Terminus-2 – DeepSeek V4 Pro (high)
Terminus-2 – GLM-4.7-Flash (thinking on)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 – DeepSeek V4 Pro (high) | DeepSeek | $0.265 | 209 of 870 planned attempts |
| Terminus-2 – GLM-4.7-Flash (thinking on) | Z.ai | $0.027 | 176 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 – DeepSeek V4 Pro (high) | DeepSeek | 8.6 min | 209 of 870 planned attempts |
| Terminus-2 – GLM-4.7-Flash (thinking on) | Z.ai | 10.0 min | 176 of 870 planned attempts |
Frequently asked questions
- Which scores higher on the Geospatial Agent Index, Terminus-2 – DeepSeek V4 Pro (high) or Terminus-2 – GLM-4.7-Flash (thinking on)?
- Terminus-2 – DeepSeek V4 Pro (high), at 73 against 41 for Terminus-2 – GLM-4.7-Flash (thinking on). Terminus-2 – DeepSeek V4 Pro (high): 209 of 870 planned attempts. Terminus-2 – GLM-4.7-Flash (thinking on): 176 of 870 planned attempts. Coverage is partial; scores can change as more attempts are decided.
- Which is cheaper per task, Terminus-2 – DeepSeek V4 Pro (high) or Terminus-2 – GLM-4.7-Flash (thinking on)?
- Terminus-2 – GLM-4.7-Flash (thinking on), at $0.027 against $0.265 for Terminus-2 – DeepSeek V4 Pro (high).
- Which is faster per task, Terminus-2 – DeepSeek V4 Pro (high) or Terminus-2 – GLM-4.7-Flash (thinking on)?
- Terminus-2 – DeepSeek V4 Pro (high), at 8.6 min against 10.0 min for Terminus-2 – GLM-4.7-Flash (thinking on).
- Which has the larger context window, Terminus-2 – DeepSeek V4 Pro (high) or Terminus-2 – GLM-4.7-Flash (thinking on)?
- Terminus-2 – DeepSeek V4 Pro (high), at 1,048,576 tokens against 131,072 tokens for Terminus-2 – GLM-4.7-Flash (thinking on).
More: Terminus-2 – DeepSeek V4 Pro (high) · Terminus-2 – GLM-4.7-Flash (thinking on) · all comparisons