Which scores higher on the Geospatial Agent Index, Terminus-2 – DeepSeek V4 Pro (high) or Terminus-2 – Gemini 3.1 Flash-Lite (minimal)?

Terminus-2 – DeepSeek V4 Pro (high), at 74 against 34 for Terminus-2 – Gemini 3.1 Flash-Lite (minimal). Terminus-2 – DeepSeek V4 Pro (high): 870 of 870 planned attempts. Terminus-2 – Gemini 3.1 Flash-Lite (minimal): 869 of 870 planned attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Terminus-2 – DeepSeek V4 Pro (high) or Terminus-2 – Gemini 3.1 Flash-Lite (minimal)?

Terminus-2 – Gemini 3.1 Flash-Lite (minimal), at $0.0056 against $0.273 for Terminus-2 – DeepSeek V4 Pro (high).

Which is faster per task, Terminus-2 – DeepSeek V4 Pro (high) or Terminus-2 – Gemini 3.1 Flash-Lite (minimal)?

Terminus-2 – Gemini 3.1 Flash-Lite (minimal), at 0.5 min against 7.4 min for Terminus-2 – DeepSeek V4 Pro (high).

Which has the larger context window, Terminus-2 – DeepSeek V4 Pro (high) or Terminus-2 – Gemini 3.1 Flash-Lite (minimal)?

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

Terminus-2 – DeepSeek V4 Pro (high) vs. Terminus-2 – Gemini 3.1 Flash-Lite (minimal): geospatial agent comparison

Comparison between Terminus-2 – DeepSeek V4 Pro (high) and Terminus-2 – Gemini 3.1 Flash-Lite (minimal) 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 – DeepSeek V4 Pro (high) vs. Terminus-2 – Gemini 3.1 Flash-Lite (minimal)
Metric	Terminus-2 – DeepSeek V4 Pro (high)	Terminus-2 – Gemini 3.1 Flash-Lite (minimal)
Geospatial Agent Index	74 (attempts per task: 3)	34* (attempts per task: 3)
GeoAgentBench score	95	33
GeoBenchX score	54	40
Earth-Bench score	53	28
GeoAnalystBench score	95	37
Raster and remote sensing score	74	30
Vector and overlay score	72	22
Networks and routing score	93	0
Climate and time series score	71	43
Spatial statistics and interpolation score	50	17
Mapping and cartography score	70	39
Recognising infeasible requests score	46	50
Cost per task	$0.273	$0.0056
Time per task	7.4 min	0.5 min
Tokens per attempt	216k	18k
Turns per attempt	12.8	3.5
Attempts decided	870	869
Input price per 1M tokens	$1.32	$0.25
Output price per 1M tokens	$3.96	$1.50
Context window	1,048,576	1,048,576
Image input	No	Yes
Developer	DeepSeek	Google

Charts

Geospatial Agent Index

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

Partial coverage

Data table: Geospatial Agent Index

Geospatial Agent Index
Model	Creator	Geospatial Agent Index	Range while attempts are pending	Benchmarks covered	Coverage (attempts)
Terminus-2 – DeepSeek V4 Pro (high)	DeepSeek	74 (attempts per task: 3)	No pending judgements	4 of 4	870 of 870 planned attempts
Terminus-2 – Gemini 3.1 Flash-Lite (minimal)	Google	34* (attempts per task: 3)	No pending judgements; coverage incomplete	4 of 4	869 of 870 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

Partial coverage

Data table: Cost per task

Cost per task
Model	Creator	Cost per task	Coverage (attempts)
Terminus-2 – DeepSeek V4 Pro (high)	DeepSeek	$0.273	870 of 870 planned attempts
Terminus-2 – Gemini 3.1 Flash-Lite (minimal)	Google	$0.0056	869 of 870 planned attempts

Time per task

Average agent wall time per task · Lower is better

Partial coverage

Data table: Time per task

Time per task
Model	Creator	Time per task	Coverage (attempts)
Terminus-2 – DeepSeek V4 Pro (high)	DeepSeek	7.4 min	870 of 870 planned attempts
Terminus-2 – Gemini 3.1 Flash-Lite (minimal)	Google	0.5 min	869 of 870 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – DeepSeek V4 Pro (high) or Terminus-2 – Gemini 3.1 Flash-Lite (minimal)?: Terminus-2 – DeepSeek V4 Pro (high), at 74 against 34 for Terminus-2 – Gemini 3.1 Flash-Lite (minimal). Terminus-2 – DeepSeek V4 Pro (high): 870 of 870 planned attempts. Terminus-2 – Gemini 3.1 Flash-Lite (minimal): 869 of 870 planned attempts. Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – DeepSeek V4 Pro (high) or Terminus-2 – Gemini 3.1 Flash-Lite (minimal)?: Terminus-2 – Gemini 3.1 Flash-Lite (minimal), at $0.0056 against $0.273 for Terminus-2 – DeepSeek V4 Pro (high).
Which is faster per task, Terminus-2 – DeepSeek V4 Pro (high) or Terminus-2 – Gemini 3.1 Flash-Lite (minimal)?: Terminus-2 – Gemini 3.1 Flash-Lite (minimal), at 0.5 min against 7.4 min for Terminus-2 – DeepSeek V4 Pro (high).
Which has the larger context window, Terminus-2 – DeepSeek V4 Pro (high) or Terminus-2 – Gemini 3.1 Flash-Lite (minimal)?: They are level, at 1,048,576 tokens.

More: Terminus-2 – DeepSeek V4 Pro (high) · Terminus-2 – Gemini 3.1 Flash-Lite (minimal) · all comparisons