Gemini 3.1 Pro (preview) (low) vs Qwen 3.6 35B-A3B (Reasoning)
Results updated 5 November 2026 · In Terminus-2 and Qwen Code, so part of any gap can come from the harness · How we benchmark
Verdict
Not comparable yet: Gemini 3.1 Pro (preview) (low) is not yet ranked.
- Cost per task
- $0.057 vs $0.00
- Time per task
- 0.5 min vs 2.9 min (estimated)
- Tokens per attempt
- 19k vs 650k
- Image input
- Yes vs Yes
Gemini 3.1 Pro (preview) (low), Terminus-2 scores higher on GeoBenchX; Qwen 3.6 35B-A3B (Reasoning), Qwen Code scores higher on Earth-Bench V2. Qwen 3.6 35B-A3B (Reasoning), Qwen Code is cheaper ($0.00 against $0.057 per task), but Gemini 3.1 Pro (preview) (low), Terminus-2 is faster (0.5 min against 2.9 min).
Not yet ranked. Gemini 3.1 Pro (preview) (low), Terminus-2: no GS-QA2 score yet. Not in the Agent Index, cost and time charts until it has a score on every index evaluation. Results so far are in the side-by-side table.
Where they differ most
By kind of work, share of tasks passed, 0 to 100 · Higher is better
| Kind of work | Gemini 3.1 Pro (preview) (low) | Qwen 3.6 35B-A3B (Reasoning) |
|---|---|---|
| Change detection | 25 | 68 |
| GIS analysis | 80 | 56 |
| Climate and time series | 45 | 64 |
| Remote sensing and raster analysis | 59 | 65 |
Where the tasks are set: each kind of work links to its tasks and scoresCharts for each: Gemini 3.1 Pro (preview) (low), Terminus-2 · Qwen 3.6 35B-A3B (Reasoning), Qwen Code.
Side by side
| Metric | Gemini 3.1 Pro (preview) (low), Terminus-2 | Qwen 3.6 35B-A3B (Reasoning), Qwen Code |
|---|---|---|
| Geospatial Agent Index: Text only | 57 | 57 |
| Geospatial Agent Index: Text + vision | No data | No data |
| Earth-Bench V2 score | 41 | 60 |
| GeoBenchX score | 74 | 50 |
| GS-QA2 score | No data | 62 |
| Vision agents score | No data | No data |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 84 | 65 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 79 | 47 |
| OGD4All score (standalone; in no index) | No data | 93 |
| GeoNatureAgent score (standalone; in no index) | No data | 79 |
| MultiGlobeQA score (standalone; in no index) | No data | 72 |
| GeoAgentEval score (standalone; in no index) | No data | 68 |
| ImpactMesh score (standalone; in no index) | No data | No data |
| Remote sensing and raster analysis score | 59 | 65 |
| Change detection score | 25 | 68 |
| GIS analysis score | 80 | 56 |
| Climate and time series score | 45 | 64 |
| Making maps score | 60 | 59 |
| Cost per task | $0.057 | $0.00 |
| Time per task (at 100 output tokens/s) | 0.5 min | 2.9 min (estimated) |
| Tokens per attempt | 19k | 650k |
| Turns per attempt | 3.6 | 16.9 |
| Input price per 1M tokens | $2.00 | $0.25 |
| Output price per 1M tokens | $12.00 | $1.49 |
| Context window | 1,048,576 | 262,144 |
| Image input | Yes | Yes |
| Developer | Alibaba (Qwen) |