Terminus-2 – gpt-oss-120b (high) vs. Terminus-2 – Kimi K2.7 Code (Reasoning): geospatial agent comparison
Comparison between Terminus-2 – gpt-oss-120b (high) and Terminus-2 – Kimi K2.7 Code (Reasoning) 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 (Reasoning) |
|---|---|---|
| Geospatial Agent Index | 53* | 73* |
| GeoAgentBench score | 70 | 90 |
| GeoBenchX score | 42 | 54 |
| Earth-Bench score | 46 | 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 | 62 | 79 |
| Spatial statistics and interpolation score | 30 | 63 |
| Mapping and cartography score | 43 | 70 |
| Recognising infeasible requests score | 47 | 41 |
| Cost per task | $0.026 | $0.126 |
| Time per task | 4.6 min | 6.7 min |
| Tokens per attempt | 59k | 309k |
| Turns per attempt | 5.3 | 14.5 |
| Attempts decided | 249 | 249 |
| 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 (Reasoning) | Moonshot AI | 73* | No pending judgements; coverage incomplete | 4 of 4 | 249 of 870 planned attempts |
| Terminus-2 – gpt-oss-120b (high) | OpenAI | 53* | No pending judgements; coverage incomplete | 4 of 4 | 249 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 – gpt-oss-120b (high) | OpenAI | $0.026 | 249 of 870 planned attempts |
| Terminus-2 – Kimi K2.7 Code (Reasoning) | Moonshot AI | $0.126 | 249 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 | 4.6 min | 249 of 870 planned attempts |
| Terminus-2 – Kimi K2.7 Code (Reasoning) | Moonshot AI | 6.7 min | 249 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 (Reasoning)?
- Terminus-2 – Kimi K2.7 Code (Reasoning), at 73 against 53 for Terminus-2 – gpt-oss-120b (high). Terminus-2 – gpt-oss-120b (high): 249 of 870 planned attempts. Terminus-2 – Kimi K2.7 Code (Reasoning): 249 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 (Reasoning)?
- Terminus-2 – gpt-oss-120b (high), at $0.026 against $0.126 for Terminus-2 – Kimi K2.7 Code (Reasoning).
- Which is faster per task, Terminus-2 – gpt-oss-120b (high) or Terminus-2 – Kimi K2.7 Code (Reasoning)?
- Terminus-2 – gpt-oss-120b (high), at 4.6 min against 6.7 min for Terminus-2 – Kimi K2.7 Code (Reasoning).
- Which has the larger context window, Terminus-2 – gpt-oss-120b (high) or Terminus-2 – Kimi K2.7 Code (Reasoning)?
- Terminus-2 – Kimi K2.7 Code (Reasoning), 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 (Reasoning) · all comparisons