Which scores higher on the Geospatial Agent Index, Terminus-2 – Gemma 4 26B A4B (thinking on) or Claude Code – Claude Haiku 5.5 (xhigh)?

Claude Code – Claude Haiku 5.5 (xhigh), at 78 against 62 for Terminus-2 – Gemma 4 26B A4B (thinking on). Terminus-2 – Gemma 4 26B A4B (thinking on): 870 of 870 planned attempts. Claude Code – Claude Haiku 5.5 (xhigh): 290 of 290 planned attempts.

Which is cheaper per task, Terminus-2 – Gemma 4 26B A4B (thinking on) or Claude Code – Claude Haiku 5.5 (xhigh)?

Terminus-2 – Gemma 4 26B A4B (thinking on), at $0.016 against $0.023 for Claude Code – Claude Haiku 5.5 (xhigh).

Which is faster per task, Terminus-2 – Gemma 4 26B A4B (thinking on) or Claude Code – Claude Haiku 5.5 (xhigh)?

Claude Code – Claude Haiku 5.5 (xhigh), at 1.9 min against 7.0 min for Terminus-2 – Gemma 4 26B A4B (thinking on).

Which has the larger context window, Terminus-2 – Gemma 4 26B A4B (thinking on) 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 – Gemma 4 26B A4B (thinking on) vs. Claude Code – Claude Haiku 5.5 (xhigh): geospatial agent comparison

Comparison between Terminus-2 – Gemma 4 26B A4B (thinking on) 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 – Gemma 4 26B A4B (thinking on) vs. Claude Code – Claude Haiku 5.5 (xhigh)
Metric	Terminus-2 – Gemma 4 26B A4B (thinking on)	Claude Code – Claude Haiku 5.5 (xhigh)
Geospatial Agent Index	62	78 (partial: 1 of 3 attempts)
GeoAgentBench score	87	100
GeoBenchX score	53	65
Earth-Bench score	34	52
GeoAnalystBench score	72	95
Raster and remote sensing score	57	73
Vector and overlay score	74	78
Networks and routing score	87	100
Climate and time series score	50	71
Spatial statistics and interpolation score	57	62
Mapping and cartography score	71	74
Recognising infeasible requests score	43	65
Cost per task	$0.016	$0.023
Time per task	7.0 min	1.9 min
Tokens per attempt	127k	635k
Turns per attempt	9.9	12.0
Attempts decided	870	290
Input price per 1M tokens	$0.10	$0.10
Output price per 1M tokens	$0.30	$0.50
Context window	256,000	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 (partial: 1 of 3 attempts)	No pending judgements	4 of 4	290 of 290 planned attempts
Terminus-2 – Gemma 4 26B A4B (thinking on)	Google	62	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 – Gemma 4 26B A4B (thinking on)	Google	$0.016	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 – Gemma 4 26B A4B (thinking on)	Google	7.0 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 – Gemma 4 26B A4B (thinking on) or Claude Code – Claude Haiku 5.5 (xhigh)?: Claude Code – Claude Haiku 5.5 (xhigh), at 78 against 62 for Terminus-2 – Gemma 4 26B A4B (thinking on). Terminus-2 – Gemma 4 26B A4B (thinking on): 870 of 870 planned attempts. Claude Code – Claude Haiku 5.5 (xhigh): 290 of 290 planned attempts.
Which is cheaper per task, Terminus-2 – Gemma 4 26B A4B (thinking on) or Claude Code – Claude Haiku 5.5 (xhigh)?: Terminus-2 – Gemma 4 26B A4B (thinking on), at $0.016 against $0.023 for Claude Code – Claude Haiku 5.5 (xhigh).
Which is faster per task, Terminus-2 – Gemma 4 26B A4B (thinking on) or Claude Code – Claude Haiku 5.5 (xhigh)?: Claude Code – Claude Haiku 5.5 (xhigh), at 1.9 min against 7.0 min for Terminus-2 – Gemma 4 26B A4B (thinking on).
Which has the larger context window, Terminus-2 – Gemma 4 26B A4B (thinking on) 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 – Gemma 4 26B A4B (thinking on) · Claude Code – Claude Haiku 5.5 (xhigh) · all comparisons