Axis Spatial

Terminus-2 – Qwen 3.8 27B (xhigh) vs. Claude Code – Claude Sonnet 5.5 (medium): geospatial agent comparison

Comparison between Terminus-2 – Qwen 3.8 27B (xhigh) and Claude Code – Claude Sonnet 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 – Qwen 3.8 27B (xhigh) vs. Claude Code – Claude Sonnet 5.5 (medium)
MetricTerminus-2 – Qwen 3.8 27B (xhigh)Claude Code – Claude Sonnet 5.5 (medium)
Geospatial Agent Index62* (partial: 0.3 of 3 attempts)77* (partial: 2 of 3 attempts)
GeoAgentBench score6098
GeoBenchX scoreNo data66
Earth-Bench score2745
GeoAnalystBench score10097
Raster and remote sensing score3670
Vector and overlay score7881
Networks and routing score67100
Climate and time series score4365
Spatial statistics and interpolation score6279
Mapping and cartography score10078
Recognising infeasible requests scoreNo data59
Cost per task$0.066$0.052
Time per task19.8 min0.6 min
Tokens per attempt90k72k
Turns per attempt8.23.7
Attempts decided101500
Input price per 1M tokens$0.45$2.00
Output price per 1M tokens$3.20$10.00
Context window262,144No data
Image inputYesNo data
DeveloperAlibaba (Qwen)Anthropic

Charts

Geospatial Agent Index

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

  • Partial coverage
Geospatial Agent IndexClaude Code – Claude Sonnet 5.5 (medium): 77* (partial coverage); Terminus-2 – Qwen 3.8 27B (xhigh): 62* (partial coverage)025507510077*Claude Sonnet 5.5 (medium)62*Qwen 3.8 27B (xhigh)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Claude Code – Claude Sonnet 5.5 (medium)Anthropic77* (partial: 2 of 3 attempts)67 to 774 of 4500 of 870 planned attempts (229 excluded)
Terminus-2 – Qwen 3.8 27B (xhigh)Alibaba (Qwen)62* (partial: 0.3 of 3 attempts)No pending judgements; coverage incomplete3 of 4101 of 870 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskClaude Code – Claude Sonnet 5.5 (medium): $0.052 (partial coverage); Terminus-2 – Qwen 3.8 27B (xhigh): $0.066 (partial coverage)$0$0.020$0.040$0.060$0.080$0.052Claude Sonnet 5.5 (medium)$0.066Qwen 3.8 27B (xhigh)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – Qwen 3.8 27B (xhigh)Alibaba (Qwen)$0.066101 of 870 planned attempts
Claude Code – Claude Sonnet 5.5 (medium)Anthropic$0.052568 of 870 planned attempts (229 excluded)

Time per task

Average agent wall time per task · Lower is better

  • Partial coverage
Time per taskClaude Code – Claude Sonnet 5.5 (medium): 0.6 min (partial coverage); Terminus-2 – Qwen 3.8 27B (xhigh): 19.8 min (partial coverage)0m5m10m15m20m0.6 minClaude Sonnet 5.5 (medium)19.8 minQwen 3.8 27B (xhigh)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Terminus-2 – Qwen 3.8 27B (xhigh)Alibaba (Qwen)19.8 min101 of 870 planned attempts
Claude Code – Claude Sonnet 5.5 (medium)Anthropic0.6 min568 of 870 planned attempts (229 excluded)

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – Qwen 3.8 27B (xhigh) or Claude Code – Claude Sonnet 5.5 (medium)?
Not comparable yet: Terminus-2 – Qwen 3.8 27B (xhigh) has scores on 3 of 4 benchmarks, so it is not yet ranked. Terminus-2 – Qwen 3.8 27B (xhigh): 101 of 870 planned attempts. Claude Code – Claude Sonnet 5.5 (medium): 500 of 870 planned attempts (229 excluded). Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – Qwen 3.8 27B (xhigh) or Claude Code – Claude Sonnet 5.5 (medium)?
Claude Code – Claude Sonnet 5.5 (medium), at $0.052 against $0.066 for Terminus-2 – Qwen 3.8 27B (xhigh).
Which is faster per task, Terminus-2 – Qwen 3.8 27B (xhigh) or Claude Code – Claude Sonnet 5.5 (medium)?
Claude Code – Claude Sonnet 5.5 (medium), at 0.6 min against 19.8 min for Terminus-2 – Qwen 3.8 27B (xhigh).
Which has the larger context window, Terminus-2 – Qwen 3.8 27B (xhigh) or Claude Code – Claude Sonnet 5.5 (medium)?
Not known yet: Claude Code – Claude Sonnet 5.5 (medium) has no context window data.

More: Terminus-2 – Qwen 3.8 27B (xhigh) · Claude Code – Claude Sonnet 5.5 (medium) · all comparisons