Axis Spatial

Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high) vs. Claude Code – GLM-5.2 (max): geospatial agent comparison

Comparison between Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high) and Claude Code – GLM-5.2 (max) 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 – Claude Sonnet 4.6 (adaptive, effort high) vs. Claude Code – GLM-5.2 (max)
MetricTerminus-2 – Claude Sonnet 4.6 (adaptive, effort high)Claude Code – GLM-5.2 (max)
Geospatial Agent Index40* (partial: attempt 1 on 209 of 565 tasks)53* (partial: attempt 1 on 200 of 565 tasks)
Earth-Bench V2 score3963
GeoBenchX score4042
GS-QA2 scoreNo dataNo data
GeoAgentBench score (guided GIS workflow; outside the index)96No data
GeoAnalystBench score (guided GIS workflow; outside the index)84No data
Raster and remote sensing score3862
Vector and overlay score3340
Networks and routing scoreNo dataNo data
Climate and time series score5867
Spatial statistics and interpolation score0No data
Mapping and cartography score63No data
Recognising infeasible requests score2941
Cost per task$0.291$0.437
Time per task3.9 min7.1 min
Tokens per attempt80k827k
Turns per attempt7.018.7
Attempts decided209120
Input price per 1M tokens$3.00$1.40
Output price per 1M tokens$15.00$4.40
Context window1,000,000262,144
Image inputYesNo
DeveloperAnthropicZ.ai

Charts

Partial coverage. Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high): 36 of 147 Earth-Bench V2 tasks; GS-QA2 incomplete; Claude Code – GLM-5.2 (max): 35 of 147 Earth-Bench V2 tasks; 165 of 173 GeoBenchX tasks; GS-QA2 incomplete. Grey placeholders identify these entries in the index, cost and output token charts; their height does not represent a value. Comparable bars appear when first-attempt coverage is complete. Their available results remain in the side-by-side table.

Geospatial Agent Index

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

Geospatial Agent IndexTerminus-2 – Claude Sonnet 4.6 (adaptive, effort high): Partial; Claude Code – GLM-5.2 (max): Partial0255075100PartialClaude Sonnet 4.6 (adaptive, effort high)PartialGLM-5.2 (max)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)

Cost per task

Average cost per task (USD) · Lower is better

Cost per taskTerminus-2 – Claude Sonnet 4.6 (adaptive, effort high): Partial; Claude Code – GLM-5.2 (max): Partial$0$0.250$0.500$0.750$1.00PartialClaude Sonnet 4.6 (adaptive, effort high)PartialGLM-5.2 (max)
How to read this chart

Not shown: partial coverage. Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high), Claude Code – GLM-5.2 (max).

Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)

Output tokens per task

Average output tokens per attempt, reasoning included · Lower is better

Output tokens per taskTerminus-2 – Claude Sonnet 4.6 (adaptive, effort high): Partial; Claude Code – GLM-5.2 (max): Partial00011PartialClaude Sonnet 4.6 (adaptive, effort high)PartialGLM-5.2 (max)
How to read this chart

Not shown: partial coverage. Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high), Claude Code – GLM-5.2 (max).

Data table: Output tokens per task
Output tokens per task
ModelCreatorOutput tokens per taskCoverage (attempts)

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high) or Claude Code – GLM-5.2 (max)?
Not comparable yet: Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high) has partial coverage (36 of 147 Earth-Bench V2 tasks; GS-QA2 incomplete) and Claude Code – GLM-5.2 (max) has partial coverage (35 of 147 Earth-Bench V2 tasks; 165 of 173 GeoBenchX tasks; GS-QA2 incomplete), so it is not ranked. Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high): 209 of 614 planned attempts (91 excluded). Claude Code – GLM-5.2 (max): 120 of 614 planned attempts (9 excluded). Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high) or Claude Code – GLM-5.2 (max)?
Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high), at $0.291 against $0.437 for Claude Code – GLM-5.2 (max).
Which writes fewer output tokens per task, Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high) or Claude Code – GLM-5.2 (max)?
Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high), at 13k against 34k for Claude Code – GLM-5.2 (max).
Which has the larger context window, Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high) or Claude Code – GLM-5.2 (max)?
Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high), at 1,000,000 tokens against 262,144 tokens for Claude Code – GLM-5.2 (max).

More: Terminus-2 – Claude Sonnet 4.6 (adaptive, effort high) · Claude Code – GLM-5.2 (max) · all comparisons