Axis Spatial

Terminus-2 – GLM-5.2 (max) vs. Terminus-2 – GLM-5.3-Flash (low): geospatial agent comparison

Comparison between Terminus-2 – GLM-5.2 (max) and Terminus-2 – GLM-5.3-Flash (low) 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 (max) vs. Terminus-2 – GLM-5.3-Flash (low)
MetricTerminus-2 – GLM-5.2 (max)Terminus-2 – GLM-5.3-Flash (low)
Geospatial Agent Index75* (partial: 1.1 of 3 attempts)66* (partial: 1.1 of 3 attempts)
GeoAgentBench score9794
GeoBenchX score5547
Earth-Bench score5227
GeoAnalystBench score9594
Raster and remote sensing score7361
Vector and overlay score8169
Networks and routing score100100
Climate and time series score7954
Spatial statistics and interpolation score7548
Mapping and cartography score7267
Recognising infeasible requests score3735
Cost per task$0.362$0.028
Time per task9.3 min9.8 min
Tokens per attempt363k278k
Turns per attempt12.012.1
Attempts decided306288
Input price per 1M tokens$1.40$0.15
Output price per 1M tokens$4.40$0.50
Context window262,1441,048,576
Image inputNoYes
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-5.2 (max): 75* (partial coverage); Terminus-2 – GLM-5.3-Flash (low): 66* (partial coverage)025507510075*GLM-5.2 (max)66*GLM-5.3-Flash (low)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Terminus-2 – GLM-5.2 (max)Z.ai75* (partial: 1.1 of 3 attempts)72 to 754 of 4306 of 870 planned attempts
Terminus-2 – GLM-5.3-Flash (low)Z.ai66* (partial: 1.1 of 3 attempts)59 to 674 of 4288 of 870 planned attempts (3 excluded)

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskTerminus-2 – GLM-5.3-Flash (low): $0.028 (partial coverage); Terminus-2 – GLM-5.2 (max): $0.362 (partial coverage)$0$0.100$0.200$0.300$0.400$0.028GLM-5.3-Flash (low)$0.362GLM-5.2 (max)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – GLM-5.2 (max)Z.ai$0.362324 of 870 planned attempts
Terminus-2 – GLM-5.3-Flash (low)Z.ai$0.028325 of 870 planned attempts (3 excluded)

Time per task

Average agent wall time per task · Lower is better

  • Partial coverage
Time per taskTerminus-2 – GLM-5.2 (max): 9.3 min (partial coverage); Terminus-2 – GLM-5.3-Flash (low): 9.8 min (partial coverage)0m2m5m8m10m9.3 minGLM-5.2 (max)9.8 minGLM-5.3-Flash (low)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Terminus-2 – GLM-5.2 (max)Z.ai9.3 min324 of 870 planned attempts
Terminus-2 – GLM-5.3-Flash (low)Z.ai9.8 min325 of 870 planned attempts (3 excluded)

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – GLM-5.2 (max) or Terminus-2 – GLM-5.3-Flash (low)?
Terminus-2 – GLM-5.2 (max), at 75 against 66 for Terminus-2 – GLM-5.3-Flash (low). Terminus-2 – GLM-5.2 (max): 306 of 870 planned attempts. Terminus-2 – GLM-5.3-Flash (low): 288 of 870 planned attempts (3 excluded). Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – GLM-5.2 (max) or Terminus-2 – GLM-5.3-Flash (low)?
Terminus-2 – GLM-5.3-Flash (low), at $0.028 against $0.362 for Terminus-2 – GLM-5.2 (max).
Which is faster per task, Terminus-2 – GLM-5.2 (max) or Terminus-2 – GLM-5.3-Flash (low)?
Terminus-2 – GLM-5.2 (max), at 9.3 min against 9.8 min for Terminus-2 – GLM-5.3-Flash (low).
Which has the larger context window, Terminus-2 – GLM-5.2 (max) or Terminus-2 – GLM-5.3-Flash (low)?
Terminus-2 – GLM-5.3-Flash (low), at 1,048,576 tokens against 262,144 tokens for Terminus-2 – GLM-5.2 (max).

More: Terminus-2 – GLM-5.2 (max) · Terminus-2 – GLM-5.3-Flash (low) · all comparisons