Axis Spatial

Terminus-2 – GLM-5.2 (none) vs. Claude Code – Claude Opus 5.5 (medium): geospatial agent comparison

Comparison between Terminus-2 – GLM-5.2 (none) and Claude Code – Claude Opus 5.5 (medium) 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 – GLM-5.2 (none) vs. Claude Code – Claude Opus 5.5 (medium)
MetricTerminus-2 – GLM-5.2 (none)Claude Code – Claude Opus 5.5 (medium)
Geospatial Agent Index69* (partial: 1.4 of 3 attempts)81* (partial: 1.8 of 3 attempts)
GeoAgentBench score9496
GeoBenchX score5166
Earth-Bench score5162
GeoAnalystBench score79100
Raster and remote sensing score7376
Vector and overlay score6983
Networks and routing score100100
Climate and time series score5885
Spatial statistics and interpolation score5869
Mapping and cartography score7575
Recognising infeasible requests score3360
Cost per task$0.103$0.138
Time per task2.9 min0.7 min
Tokens per attempt169k103k
Turns per attempt11.34.9
Attempts decided356461
Input price per 1M tokens$1.40$4.00
Output price per 1M tokens$4.40$20.00
Context window262,144No data
Image inputNoNo data
DeveloperZ.aiAnthropic

Charts

Geospatial Agent Index

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

  • Partial coverage
Geospatial Agent IndexClaude Code – Claude Opus 5.5 (medium): 81* (partial coverage); Terminus-2 – GLM-5.2 (none): 69* (partial coverage)025507510081*Claude Opus 5.5 (medium)69*GLM-5.2 (none)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Claude Code – Claude Opus 5.5 (medium)Anthropic81* (partial: 1.8 of 3 attempts)70 to 814 of 4461 of 870 planned attempts
Terminus-2 – GLM-5.2 (none)Z.ai69* (partial: 1.4 of 3 attempts)62 to 724 of 4356 of 870 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskTerminus-2 – GLM-5.2 (none): $0.103 (partial coverage); Claude Code – Claude Opus 5.5 (medium): $0.138 (partial coverage)$0$0.038$0.075$0.113$0.150$0.103GLM-5.2 (none)$0.138Claude Opus 5.5 (medium)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – GLM-5.2 (none)Z.ai$0.103408 of 870 planned attempts
Claude Code – Claude Opus 5.5 (medium)Anthropic$0.138532 of 870 planned attempts

Time per task

Average agent wall time per task · Lower is better

  • Partial coverage
Time per taskClaude Code – Claude Opus 5.5 (medium): 0.7 min (partial coverage); Terminus-2 – GLM-5.2 (none): 2.9 min (partial coverage)0m1m2m2m3m0.7 minClaude Opus 5.5 (medium)2.9 minGLM-5.2 (none)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Terminus-2 – GLM-5.2 (none)Z.ai2.9 min408 of 870 planned attempts
Claude Code – Claude Opus 5.5 (medium)Anthropic0.7 min532 of 870 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – GLM-5.2 (none) or Claude Code – Claude Opus 5.5 (medium)?
Claude Code – Claude Opus 5.5 (medium), at 81 against 69 for Terminus-2 – GLM-5.2 (none). Terminus-2 – GLM-5.2 (none): 356 of 870 planned attempts. Claude Code – Claude Opus 5.5 (medium): 461 of 870 planned attempts. Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – GLM-5.2 (none) or Claude Code – Claude Opus 5.5 (medium)?
Terminus-2 – GLM-5.2 (none), at $0.103 against $0.138 for Claude Code – Claude Opus 5.5 (medium).
Which is faster per task, Terminus-2 – GLM-5.2 (none) or Claude Code – Claude Opus 5.5 (medium)?
Claude Code – Claude Opus 5.5 (medium), at 0.7 min against 2.9 min for Terminus-2 – GLM-5.2 (none).
Which has the larger context window, Terminus-2 – GLM-5.2 (none) or Claude Code – Claude Opus 5.5 (medium)?
Not known yet: Claude Code – Claude Opus 5.5 (medium) has no context window data.

More: Terminus-2 – GLM-5.2 (none) · Claude Code – Claude Opus 5.5 (medium) · all comparisons