Which scores higher on the Geospatial Agent Index, Terminus-2 – Gemini 3.1 Pro (preview) (high) or Claude Code – Claude Haiku 5.5 (xhigh)?

Claude Code – Claude Haiku 5.5 (xhigh), at 78 against 75 for Terminus-2 – Gemini 3.1 Pro (preview) (high). Terminus-2 – Gemini 3.1 Pro (preview) (high): 870 of 870 planned attempts. Claude Code – Claude Haiku 5.5 (xhigh): 290 of 290 planned attempts.

Which is cheaper per task, Terminus-2 – Gemini 3.1 Pro (preview) (high) or Claude Code – Claude Haiku 5.5 (xhigh)?

Claude Code – Claude Haiku 5.5 (xhigh), at $0.023 against $0.252 for Terminus-2 – Gemini 3.1 Pro (preview) (high).

Which is faster per task, Terminus-2 – Gemini 3.1 Pro (preview) (high) or Claude Code – Claude Haiku 5.5 (xhigh)?

Claude Code – Claude Haiku 5.5 (xhigh), at 1.9 min against 3.4 min for Terminus-2 – Gemini 3.1 Pro (preview) (high).

Which has the larger context window, Terminus-2 – Gemini 3.1 Pro (preview) (high) or Claude Code – Claude Haiku 5.5 (xhigh)?

Not known yet: Claude Code – Claude Haiku 5.5 (xhigh) has no context window data.

Terminus-2 – Gemini 3.1 Pro (preview) (high) vs. Claude Code – Claude Haiku 5.5 (xhigh): geospatial agent comparison

Comparison between Terminus-2 – Gemini 3.1 Pro (preview) (high) and Claude Code – Claude Haiku 5.5 (xhigh) 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 Pro (preview) (high) vs. Claude Code – Claude Haiku 5.5 (xhigh)
Metric	Terminus-2 – Gemini 3.1 Pro (preview) (high)	Claude Code – Claude Haiku 5.5 (xhigh)
Geospatial Agent Index	75 (attempts per task: 3)	78 (attempts per task: 1)
GeoAgentBench score	94	100
GeoBenchX score	65	65
Earth-Bench score	54	52
GeoAnalystBench score	86	95
Raster and remote sensing score	67	73
Vector and overlay score	78	78
Networks and routing score	93	100
Climate and time series score	82	71
Spatial statistics and interpolation score	72	62
Mapping and cartography score	57	74
Recognising infeasible requests score	75	65
Cost per task	$0.252	$0.023
Time per task	3.4 min	1.9 min
Tokens per attempt	73k	635k
Turns per attempt	7.1	12.0
Attempts decided	870	290
Input price per 1M tokens	$2.00	$0.10
Output price per 1M tokens	$12.00	$0.50
Context window	1,048,576	No data
Image input	Yes	No data
Developer	Google	Anthropic

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)
Claude Code – Claude Haiku 5.5 (xhigh)	Anthropic	78 (attempts per task: 1)	No pending judgements	4 of 4	290 of 290 planned attempts
Terminus-2 – Gemini 3.1 Pro (preview) (high)	Google	75 (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 Pro (preview) (high)	Google	$0.252	870 of 870 planned attempts
Claude Code – Claude Haiku 5.5 (xhigh)	Anthropic	$0.023	290 of 290 planned attempts

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 Pro (preview) (high)	Google	3.4 min	870 of 870 planned attempts
Claude Code – Claude Haiku 5.5 (xhigh)	Anthropic	1.9 min	290 of 290 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – Gemini 3.1 Pro (preview) (high) or Claude Code – Claude Haiku 5.5 (xhigh)?: Claude Code – Claude Haiku 5.5 (xhigh), at 78 against 75 for Terminus-2 – Gemini 3.1 Pro (preview) (high). Terminus-2 – Gemini 3.1 Pro (preview) (high): 870 of 870 planned attempts. Claude Code – Claude Haiku 5.5 (xhigh): 290 of 290 planned attempts.
Which is cheaper per task, Terminus-2 – Gemini 3.1 Pro (preview) (high) or Claude Code – Claude Haiku 5.5 (xhigh)?: Claude Code – Claude Haiku 5.5 (xhigh), at $0.023 against $0.252 for Terminus-2 – Gemini 3.1 Pro (preview) (high).
Which is faster per task, Terminus-2 – Gemini 3.1 Pro (preview) (high) or Claude Code – Claude Haiku 5.5 (xhigh)?: Claude Code – Claude Haiku 5.5 (xhigh), at 1.9 min against 3.4 min for Terminus-2 – Gemini 3.1 Pro (preview) (high).
Which has the larger context window, Terminus-2 – Gemini 3.1 Pro (preview) (high) or Claude Code – Claude Haiku 5.5 (xhigh)?: Not known yet: Claude Code – Claude Haiku 5.5 (xhigh) has no context window data.

More: Terminus-2 – Gemini 3.1 Pro (preview) (high) · Claude Code – Claude Haiku 5.5 (xhigh) · all comparisons