Which scores higher on the Geospatial Agent Index, Terminus-2 – Gemini 3.1 Flash-Lite (low) or Terminus-2 – Gemini 3.1 Pro (preview) (low)?

Terminus-2 – Gemini 3.1 Pro (preview) (low), at 65 against 49 for Terminus-2 – Gemini 3.1 Flash-Lite (low). Terminus-2 – Gemini 3.1 Flash-Lite (low): 870 of 870 planned attempts. Terminus-2 – Gemini 3.1 Pro (preview) (low): 870 of 870 planned attempts (22 excluded).

Which is cheaper per task, Terminus-2 – Gemini 3.1 Flash-Lite (low) or Terminus-2 – Gemini 3.1 Pro (preview) (low)?

Terminus-2 – Gemini 3.1 Flash-Lite (low), at $0.012 against $0.061 for Terminus-2 – Gemini 3.1 Pro (preview) (low).

Which is faster per task, Terminus-2 – Gemini 3.1 Flash-Lite (low) or Terminus-2 – Gemini 3.1 Pro (preview) (low)?

Terminus-2 – Gemini 3.1 Pro (preview) (low), at 1.0 min against 1.0 min for Terminus-2 – Gemini 3.1 Flash-Lite (low).

Which has the larger context window, Terminus-2 – Gemini 3.1 Flash-Lite (low) or Terminus-2 – Gemini 3.1 Pro (preview) (low)?

They are level, at 1,048,576 tokens.

Terminus-2 – Gemini 3.1 Flash-Lite (low) vs. Terminus-2 – Gemini 3.1 Pro (preview) (low): geospatial agent comparison

Comparison between Terminus-2 – Gemini 3.1 Flash-Lite (low) and Terminus-2 – Gemini 3.1 Pro (preview) (low) on the Geospatial Agent Index, each benchmark, cost, time and token use, from the same tasks, agent and limits. Methodology.

Side by side

Terminus-2 – Gemini 3.1 Flash-Lite (low) vs. Terminus-2 – Gemini 3.1 Pro (preview) (low)
Metric	Terminus-2 – Gemini 3.1 Flash-Lite (low)	Terminus-2 – Gemini 3.1 Pro (preview) (low)
Geospatial Agent Index	49 (attempts per task: 3)	65 (attempts per task: 3)
GeoAgentBench score	52	83
GeoBenchX score	46	61
Earth-Bench score	40	42
GeoAnalystBench score	60	75
Raster and remote sensing score	46	58
Vector and overlay score	46	69
Networks and routing score	53	93
Climate and time series score	56	67
Spatial statistics and interpolation score	29	51
Mapping and cartography score	50	55
Recognising infeasible requests score	48	71
Cost per task	$0.012	$0.061
Time per task	1.0 min	1.0 min
Tokens per attempt	37k	19k
Turns per attempt	5.1	3.8
Attempts decided	870	870
Input price per 1M tokens	$0.25	$2.00
Output price per 1M tokens	$1.50	$12.00
Context window	1,048,576	1,048,576
Image input	Yes	Yes
Developer	Google	Google

Charts

Geospatial Agent Index

Equal-weight average of the evaluation scores, 0 to 100 · Higher is better

Data table: Geospatial Agent Index

Geospatial Agent Index
Model	Creator	Geospatial Agent Index	Range while attempts are pending	Benchmarks covered	Coverage (attempts)
Terminus-2 – Gemini 3.1 Pro (preview) (low)	Google	65 (attempts per task: 3)	No pending judgements	4 of 4	870 of 870 planned attempts (22 excluded)
Terminus-2 – Gemini 3.1 Flash-Lite (low)	Google	49 (attempts per task: 3)	No pending judgements	4 of 4	870 of 870 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

Data table: Cost per task

Cost per task
Model	Creator	Cost per task	Coverage (attempts)
Terminus-2 – Gemini 3.1 Flash-Lite (low)	Google	$0.012	870 of 870 planned attempts
Terminus-2 – Gemini 3.1 Pro (preview) (low)	Google	$0.061	870 of 870 planned attempts (22 excluded)

Time per task

Average agent wall time per task · Lower is better

Data table: Time per task

Time per task
Model	Creator	Time per task	Coverage (attempts)
Terminus-2 – Gemini 3.1 Flash-Lite (low)	Google	1.0 min	870 of 870 planned attempts
Terminus-2 – Gemini 3.1 Pro (preview) (low)	Google	1.0 min	870 of 870 planned attempts (22 excluded)

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – Gemini 3.1 Flash-Lite (low) or Terminus-2 – Gemini 3.1 Pro (preview) (low)?: Terminus-2 – Gemini 3.1 Pro (preview) (low), at 65 against 49 for Terminus-2 – Gemini 3.1 Flash-Lite (low). Terminus-2 – Gemini 3.1 Flash-Lite (low): 870 of 870 planned attempts. Terminus-2 – Gemini 3.1 Pro (preview) (low): 870 of 870 planned attempts (22 excluded).
Which is cheaper per task, Terminus-2 – Gemini 3.1 Flash-Lite (low) or Terminus-2 – Gemini 3.1 Pro (preview) (low)?: Terminus-2 – Gemini 3.1 Flash-Lite (low), at $0.012 against $0.061 for Terminus-2 – Gemini 3.1 Pro (preview) (low).
Which is faster per task, Terminus-2 – Gemini 3.1 Flash-Lite (low) or Terminus-2 – Gemini 3.1 Pro (preview) (low)?: Terminus-2 – Gemini 3.1 Pro (preview) (low), at 1.0 min against 1.0 min for Terminus-2 – Gemini 3.1 Flash-Lite (low).
Which has the larger context window, Terminus-2 – Gemini 3.1 Flash-Lite (low) or Terminus-2 – Gemini 3.1 Pro (preview) (low)?: They are level, at 1,048,576 tokens.

More: Terminus-2 – Gemini 3.1 Flash-Lite (low) · Terminus-2 – Gemini 3.1 Pro (preview) (low) · all comparisons