Qwen 3.8 27B (xhigh), Terminus-2 vs. Step 5 Preview (Reasoning), Terminus-2
Qwen 3.8 27B (xhigh), Terminus-2 against Step 5 Preview (Reasoning), Terminus-2: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.
Side by side
| Metric | Qwen 3.8 27B (xhigh), Terminus-2 | Step 5 Preview (Reasoning), Terminus-2 |
|---|---|---|
| Geospatial Agent Index: Text only | 61 | 34 |
| Geospatial Agent Index: Text + vision | No data | No data |
| Earth-Bench V2 score | 44 | 32 |
| GeoBenchX score | 66 | 17 |
| GS-QA2 score | 74 | 52 |
| Vision agents score | No data | No data |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 60 | 50 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 89 | 53 |
| OGD4All score (standalone; in no index) | No data | No data |
| GeoNatureAgent score (standalone; in no index) | No data | No data |
| MultiGlobeQA score (standalone; in no index) | No data | No data |
| GeoAgentEval score (standalone; in no index) | No data | No data |
| Remote sensing and raster analysis score | 64 | 35 |
| GIS analysis score | 77 | 67 |
| Climate and time series score | 42 | 34 |
| Spatial statistics score | 69 | 0 |
| Making maps score | 68 | 19 |
| Recognising infeasible requests score | 57 | 24 |
| Cost per task | $0.10 | $0.071 |
| Time per task (at 100 output tokens/s) | 7.3 min | 7.9 min (estimated) |
| Tokens per attempt | 335k | 90k |
| Turns per attempt | 14.8 | 11.1 |
| Input price per 1M tokens | $0.45 | $1.00 |
| Output price per 1M tokens | $3.20 | $2.70 |
| Context window | 262,144 | 1,024,000 |
| Image input | Yes | Yes |
| Developer | Alibaba (Qwen) | StepFun |
Charts
Geospatial Agent Index
Equal average of Earth-Bench V2, GeoBenchX and GS-QA2, 0 to 100 · Higher is better
Data table: Geospatial Agent Index
| Model | Developer | Geospatial Agent Index |
|---|---|---|
| Qwen 3.8 27B (xhigh), Terminus-2 | Alibaba (Qwen) | 61 |
| Step 5 Preview (Reasoning), Terminus-2 | StepFun | 34 |
Cost per task
Average cost per task (USD) · Lower is better
Data table: Cost per task
| Model | Developer | Cost per task |
|---|---|---|
| Step 5 Preview (Reasoning), Terminus-2 | StepFun | $0.071 |
| Qwen 3.8 27B (xhigh), Terminus-2 | Alibaba (Qwen) | $0.10 |
Output tokens per task
Average output tokens per attempt, reasoning included · Lower is better
Data table: Output tokens per task
| Model | Developer | Output tokens per task |
|---|---|---|
| Step 5 Preview (Reasoning), Terminus-2 | StepFun | 10k |
| Qwen 3.8 27B (xhigh), Terminus-2 | Alibaba (Qwen) | 19k |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, Qwen 3.8 27B (xhigh), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Qwen 3.8 27B (xhigh), Terminus-2, 61 to 34.
Which is cheaper per task, Qwen 3.8 27B (xhigh), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Step 5 Preview (Reasoning), Terminus-2, $0.071 to $0.10.
Which writes fewer output tokens per task, Qwen 3.8 27B (xhigh), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Step 5 Preview (Reasoning), Terminus-2, 10k to 19k.
Which has the larger context window, Qwen 3.8 27B (xhigh), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Step 5 Preview (Reasoning), Terminus-2, 1,024,000 tokens to 262,144 tokens.
More: Qwen 3.8 27B (xhigh), Terminus-2 · Step 5 Preview (Reasoning), Terminus-2 · All comparisons