Axis Spatial

Search modelsMenu

Gemini 3.1 Pro (preview) (low) vs Gemma 4 31B (Reasoning)

Results updated 11 November 2026 · Both in Terminus-2 · How we benchmark

Verdict

Gemini 3.1 Pro (preview) (low)Not yet rankedno GS-QA2 score yet
Gemma 4 31B (Reasoning)55Geospatial Agent Index · rank 71 of 89

Not comparable yet: Gemini 3.1 Pro (preview) (low) is not yet ranked.

Cost per task
$0.057 vs $0.015
Time per task
0.5 min vs 2.1 min
Tokens per attempt
19k vs 93k
Image input
Yes vs Yes

Gemini 3.1 Pro (preview) (low), Terminus-2 scores higher on GeoBenchX; Gemma 4 31B (Reasoning), Terminus-2 scores higher on Earth-Bench V2. Gemma 4 31B (Reasoning), Terminus-2 is cheaper ($0.015 against $0.057 per task), but Gemini 3.1 Pro (preview) (low), Terminus-2 is faster (0.5 min against 2.1 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 workGemini 3.1 Pro (preview) (low)Gemma 4 31B (Reasoning)
Change detection2552
GIS analysis8056
Making maps6070
Climate and time series4547
World map of the places the tasks are setWhere the tasks are set: each kind of work links to its tasks and scores
Leaderboard

Charts for each: Gemini 3.1 Pro (preview) (low), Terminus-2 · Gemma 4 31B (Reasoning), Terminus-2.

Side by side

Gemini 3.1 Pro (preview) (low), Terminus-2 vs. Gemma 4 31B (Reasoning), Terminus-2
MetricGemini 3.1 Pro (preview) (low), Terminus-2Gemma 4 31B (Reasoning), Terminus-2
Geospatial Agent Index: Text only5755
Geospatial Agent Index: Text + visionNo dataNo data
Earth-Bench V2 score4144
GeoBenchX score7461
GS-QA2 scoreNo data61
Vision agents scoreNo dataNo data
GeoAgentBench score (Guided workflows; not in the Agent Index)8483
GeoAnalystBench score (Guided workflows; not in the Agent Index)7963
OGD4All score (standalone; in no index)No data85
GeoNatureAgent score (standalone; in no index)No data100
MultiGlobeQA score (standalone; in no index)No data30
GeoAgentEval score (standalone; in no index)No data88
ImpactMesh score (standalone; in no index)No dataNo data
Remote sensing and raster analysis score5959
Change detection score2552
GIS analysis score8056
Climate and time series score4547
Making maps score6070
Cost per task$0.057$0.015
Time per task (at 100 output tokens/s)0.5 min2.1 min
Tokens per attempt19k93k
Turns per attempt3.69.0
Input price per 1M tokens$2.00$0.17
Output price per 1M tokens$12.00$0.40
Context window1,048,576262,144
Image inputYesYes
DeveloperGoogleGoogle

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Gemini 3.1 Pro (preview) (low), Terminus-2 or Gemma 4 31B (Reasoning), Terminus-2?
Not comparable yet: Gemini 3.1 Pro (preview) (low), Terminus-2 is not yet ranked (no GS-QA2 score yet).
Which is cheaper per task, Gemini 3.1 Pro (preview) (low), Terminus-2 or Gemma 4 31B (Reasoning), Terminus-2?
Gemma 4 31B (Reasoning), Terminus-2, $0.015 to $0.057.
Which writes fewer output tokens per task, Gemini 3.1 Pro (preview) (low), Terminus-2 or Gemma 4 31B (Reasoning), Terminus-2?
Gemini 3.1 Pro (preview) (low), Terminus-2, 2k to 8k.
Which has the larger context window, Gemini 3.1 Pro (preview) (low), Terminus-2 or Gemma 4 31B (Reasoning), Terminus-2?
Gemini 3.1 Pro (preview) (low), Terminus-2, 1,048,576 tokens to 262,144 tokens.