Axis Spatial

Terminus-2 – GLM-5.3 (low) vs. Terminus-2 – GLM-5.3 (max, default): geospatial agent comparison

Comparison between Terminus-2 – GLM-5.3 (low) and Terminus-2 – GLM-5.3 (max, default) 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-5.3 (low) vs. Terminus-2 – GLM-5.3 (max, default)
MetricTerminus-2 – GLM-5.3 (low)Terminus-2 – GLM-5.3 (max, default)
Geospatial Agent Index71* (partial: 0.9 of 3 attempts)67* (partial: 1.1 of 3 attempts)
GeoAgentBench score9595
GeoBenchX score5152
Earth-Bench score3839
GeoAnalystBench score10084
Raster and remote sensing score6565
Vector and overlay score7975
Networks and routing score10080
Climate and time series score6056
Spatial statistics and interpolation score5067
Mapping and cartography score7266
Recognising infeasible requests score3842
Cost per task$0.250$0.363
Time per task6.7 min10.1 min
Tokens per attempt205k260k
Turns per attempt10.710.5
Attempts decided238310
Input price per 1M tokens$1.40$1.40
Output price per 1M tokens$4.40$4.40
Context window1,048,5761,048,576
Image inputNoNo
DeveloperZ.aiZ.ai

Charts

Geospatial Agent Index

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

  • Partial coverage
Geospatial Agent IndexTerminus-2 – GLM-5.3 (low): 71* (partial coverage); Terminus-2 – GLM-5.3 (max, default): 67* (partial coverage)025507510071*GLM-5.3 (low)67*GLM-5.3 (max, default)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Terminus-2 – GLM-5.3 (low)Z.ai71* (partial: 0.9 of 3 attempts)61 to 724 of 4238 of 290 planned attempts
Terminus-2 – GLM-5.3 (max, default)Z.ai67* (partial: 1.1 of 3 attempts)66 to 684 of 4310 of 870 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskTerminus-2 – GLM-5.3 (low): $0.250 (partial coverage); Terminus-2 – GLM-5.3 (max, default): $0.363 (partial coverage)$0$0.100$0.200$0.300$0.400$0.250GLM-5.3 (low)$0.363GLM-5.3 (max, default)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – GLM-5.3 (low)Z.ai$0.250258 of 290 planned attempts
Terminus-2 – GLM-5.3 (max, default)Z.ai$0.363320 of 870 planned attempts

Time per task

Average agent wall time per task · Lower is better

  • Partial coverage
Time per taskTerminus-2 – GLM-5.3 (low): 6.7 min (partial coverage); Terminus-2 – GLM-5.3 (max, default): 10.1 min (partial coverage)0m3m7m10m13m6.7 minGLM-5.3 (low)10.1 minGLM-5.3 (max, default)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Terminus-2 – GLM-5.3 (low)Z.ai6.7 min258 of 290 planned attempts
Terminus-2 – GLM-5.3 (max, default)Z.ai10.1 min320 of 870 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – GLM-5.3 (low) or Terminus-2 – GLM-5.3 (max, default)?
Terminus-2 – GLM-5.3 (low), at 71 against 67 for Terminus-2 – GLM-5.3 (max, default). Terminus-2 – GLM-5.3 (low): 238 of 290 planned attempts. Terminus-2 – GLM-5.3 (max, default): 310 of 870 planned attempts. Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – GLM-5.3 (low) or Terminus-2 – GLM-5.3 (max, default)?
Terminus-2 – GLM-5.3 (low), at $0.250 against $0.363 for Terminus-2 – GLM-5.3 (max, default).
Which is faster per task, Terminus-2 – GLM-5.3 (low) or Terminus-2 – GLM-5.3 (max, default)?
Terminus-2 – GLM-5.3 (low), at 6.7 min against 10.1 min for Terminus-2 – GLM-5.3 (max, default).
Which has the larger context window, Terminus-2 – GLM-5.3 (low) or Terminus-2 – GLM-5.3 (max, default)?
They are level, at 1,048,576 tokens.

More: Terminus-2 – GLM-5.3 (low) · Terminus-2 – GLM-5.3 (max, default) · all comparisons