Terminus-2 – DeepSeek V4 Pro (max) vs. Terminus-2 – Kimi K3 (always on): geospatial agent comparison
Comparison between Terminus-2 – DeepSeek V4 Pro (max) and Terminus-2 – Kimi K3 (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 – DeepSeek V4 Pro (max) | Terminus-2 – Kimi K3 (always on) |
|---|---|---|
| Geospatial Agent Index | 59* | 64* |
| Earth-Bench V2 score | 49 | 61 |
| GeoBenchX score | 57 | 55 |
| GS-QA2 score | 70 | 75 |
| GeoAgentBench score (guided GIS workflow; outside the index) | 96 | 94 |
| GeoAnalystBench score (guided GIS workflow; outside the index) | 100 | 89 |
| Raster and remote sensing score | 63 | 70 |
| Vector and overlay score | 67 | 68 |
| Networks and routing score | No data | No data |
| Climate and time series score | 51 | 66 |
| Spatial statistics and interpolation score | 43 | 50 |
| Mapping and cartography score | 80 | 78 |
| Recognising infeasible requests score | 42 | 38 |
| Cost per task | $0.341 | $0.252 |
| Time per task | 8.7 min | 3.5 min |
| Tokens per attempt | 270k | 58k |
| Turns per attempt | 14.8 | 7.4 |
| Attempts decided | 565 | 565 |
| Input price per 1M tokens | $1.32 | $3.00 |
| Output price per 1M tokens | $3.96 | $15.00 |
| Context window | 1,048,576 | 1,000,000 |
| Image input | No | Yes |
| Developer | DeepSeek | Moonshot AI |
Charts
Geospatial Agent Index
Equal-weight average of the evaluation scores, 0 to 100 · Higher is better
First eight selected entries in metric order. Full results in table view.
Data table: Geospatial Agent Index
| Model | Creator | Geospatial Agent Index | Range while attempts are pending | Benchmarks covered | Coverage (attempts) |
|---|---|---|---|---|---|
| Terminus-2 – Kimi K3 (always on) | Moonshot AI | 64* | No pending judgements; coverage incomplete; 183 results awaiting review; 1 trace review declined by the judge | 3 of 3 | 565 of 859 planned attempts |
| Terminus-2 – DeepSeek V4 Pro (max) | DeepSeek | 59* | No pending judgements; coverage incomplete; 172 results awaiting review; 1 trace review declined by the judge | 3 of 3 | 565 of 859 planned attempts |
Cost per task
Average cost per task (USD) · Lower is better
First eight selected entries in metric order. Full results in table view.
Data table: Cost per task
| Model | Creator | Cost per task | Coverage (attempts) |
|---|---|---|---|
| Terminus-2 – DeepSeek V4 Pro (max) | DeepSeek | $0.341 | 565 of 859 planned attempts |
| Terminus-2 – Kimi K3 (always on) | Moonshot AI | $0.252 | 565 of 859 planned attempts |
Output tokens per task
Average output tokens per attempt, reasoning included · Lower is better
First eight selected entries in metric order. Full results in table view.
Data table: Output tokens per task
| Model | Creator | Output tokens per task | Coverage (attempts) |
|---|---|---|---|
| Terminus-2 – DeepSeek V4 Pro (max) | DeepSeek | 24k | 565 of 859 planned attempts |
| Terminus-2 – Kimi K3 (always on) | Moonshot AI | 6k | 565 of 859 planned attempts |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, Terminus-2 – DeepSeek V4 Pro (max) or Terminus-2 – Kimi K3 (always on)?
Terminus-2 – Kimi K3 (always on), at 64 against 59 for Terminus-2 – DeepSeek V4 Pro (max). Terminus-2 – DeepSeek V4 Pro (max): 565 of 859 planned attempts. Terminus-2 – Kimi K3 (always on): 565 of 859 planned attempts. Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – DeepSeek V4 Pro (max) or Terminus-2 – Kimi K3 (always on)?
Terminus-2 – Kimi K3 (always on), at $0.252 against $0.341 for Terminus-2 – DeepSeek V4 Pro (max).
Which writes fewer output tokens per task, Terminus-2 – DeepSeek V4 Pro (max) or Terminus-2 – Kimi K3 (always on)?
Terminus-2 – Kimi K3 (always on), at 6k against 24k for Terminus-2 – DeepSeek V4 Pro (max).
Which has the larger context window, Terminus-2 – DeepSeek V4 Pro (max) or Terminus-2 – Kimi K3 (always on)?
Terminus-2 – DeepSeek V4 Pro (max), at 1,048,576 tokens against 1,000,000 tokens for Terminus-2 – Kimi K3 (always on).
More: Terminus-2 – DeepSeek V4 Pro (max) · Terminus-2 – Kimi K3 (always on) · all comparisons