Terminus-2 – gpt-oss-120b (high) vs. Terminus-2 – Kimi K2.7 Code (always on): geospatial agent comparison
Comparison between Terminus-2 – gpt-oss-120b (high) and Terminus-2 – Kimi K2.7 Code (always 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 – gpt-oss-120b (high) | Terminus-2 – Kimi K2.7 Code (always on) |
|---|---|---|
| Geospatial Agent Index | 52* | 73* |
| GeoAgentBench score | 70 | 90 |
| GeoBenchX score | 41 | 55 |
| Earth-Bench score | 45 | 62 |
| GeoAnalystBench score | 53 | 84 |
| Raster and remote sensing score | 52 | 74 |
| Vector and overlay score | 56 | 78 |
| Networks and routing score | 100 | 80 |
| Climate and time series score | 60 | 79 |
| Spatial statistics and interpolation score | 29 | 67 |
| Mapping and cartography score | 40 | 73 |
| Recognising infeasible requests score | 46 | 41 |
| Cost per task | $0.025 | $0.129 |
| Time per task | 4.4 min | 6.8 min |
| Tokens per attempt | 58k | 308k |
| Turns per attempt | 5.4 | 14.6 |
| Attempts decided | 320 | 268 |
| Input price per 1M tokens | $0.35 | $0.95 |
| Output price per 1M tokens | $0.75 | $4.00 |
| Context window | 128,000 | 262,144 |
| Image input | No | Yes |
| Developer | OpenAI | Moonshot 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 – Kimi K2.7 Code (always on) | Moonshot AI | 73* | 73 to 73 | 4 of 4 | 268 of 870 planned attempts |
| Terminus-2 – gpt-oss-120b (high) | OpenAI | 52* | 52 to 52 | 4 of 4 | 320 of 870 planned attempts |
Terminus-2 – Kimi K2.7 Code (always on)
Terminus-2 – gpt-oss-120b (high)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 – gpt-oss-120b (high) | OpenAI | $0.025 | 321 of 870 planned attempts |
| Terminus-2 – Kimi K2.7 Code (always on) | Moonshot AI | $0.129 | 269 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 – gpt-oss-120b (high) | OpenAI | 4.4 min | 321 of 870 planned attempts |
| Terminus-2 – Kimi K2.7 Code (always on) | Moonshot AI | 6.8 min | 269 of 870 planned attempts |
Frequently asked questions
- Which scores higher on the Geospatial Agent Index, Terminus-2 – gpt-oss-120b (high) or Terminus-2 – Kimi K2.7 Code (always on)?
- Terminus-2 – Kimi K2.7 Code (always on), at 73 against 52 for Terminus-2 – gpt-oss-120b (high). Terminus-2 – gpt-oss-120b (high): 320 of 870 planned attempts. Terminus-2 – Kimi K2.7 Code (always on): 268 of 870 planned attempts. Coverage is partial; scores can change as more attempts are decided.
- Which is cheaper per task, Terminus-2 – gpt-oss-120b (high) or Terminus-2 – Kimi K2.7 Code (always on)?
- Terminus-2 – gpt-oss-120b (high), at $0.025 against $0.129 for Terminus-2 – Kimi K2.7 Code (always on).
- Which is faster per task, Terminus-2 – gpt-oss-120b (high) or Terminus-2 – Kimi K2.7 Code (always on)?
- Terminus-2 – gpt-oss-120b (high), at 4.4 min against 6.8 min for Terminus-2 – Kimi K2.7 Code (always on).
- Which has the larger context window, Terminus-2 – gpt-oss-120b (high) or Terminus-2 – Kimi K2.7 Code (always on)?
- Terminus-2 – Kimi K2.7 Code (always on), at 262,144 tokens against 128,000 tokens for Terminus-2 – gpt-oss-120b (high).
More: Terminus-2 – gpt-oss-120b (high) · Terminus-2 – Kimi K2.7 Code (always on) · all comparisons