Axis Spatial

Claude Code – Claude Sonnet 5.5 (medium) vs. Claude Code – Claude Haiku 5.5 (high): geospatial agent comparison

Comparison between Claude Code – Claude Sonnet 5.5 (medium) and Claude Code – Claude Haiku 5.5 (high) on the Geospatial Agent Index, each benchmark, cost, time and token use, from the same tasks, agent and limits. Methodology.

Side by side

Claude Code – Claude Sonnet 5.5 (medium) vs. Claude Code – Claude Haiku 5.5 (high)
MetricClaude Code – Claude Sonnet 5.5 (medium)Claude Code – Claude Haiku 5.5 (high)
Geospatial Agent Index77* (partial: 2 of 3 attempts)75* (partial: 1.7 of 3 attempts)
GeoAgentBench score9898
GeoBenchX score6661
Earth-Bench score4551
GeoAnalystBench score9789
Raster and remote sensing score7069
Vector and overlay score8175
Networks and routing score100100
Climate and time series score6579
Spatial statistics and interpolation score7958
Mapping and cartography score7875
Recognising infeasible requests score5956
Cost per task$0.052$0.010
Time per task0.6 min1.1 min
Tokens per attempt72k328k
Turns per attempt3.78.1
Attempts decided500422
Input price per 1M tokens$2.00$0.10
Output price per 1M tokens$10.00$0.50
Context windowNo dataNo data
Image inputNo dataNo data
DeveloperAnthropicAnthropic

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); Claude Code – Claude Haiku 5.5 (high): 75* (partial coverage)025507510077*Claude Sonnet 5.5 (medium)75*Claude Haiku 5.5 (high)
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)
Claude Code – Claude Haiku 5.5 (high)Anthropic75* (partial: 1.7 of 3 attempts)66 to 774 of 4422 of 870 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskClaude Code – Claude Haiku 5.5 (high): $0.010 (partial coverage); Claude Code – Claude Sonnet 5.5 (medium): $0.052 (partial coverage)$0$0.015$0.030$0.045$0.060$0.010Claude Haiku 5.5 (high)$0.052Claude Sonnet 5.5 (medium)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Claude Code – Claude Sonnet 5.5 (medium)Anthropic$0.052568 of 870 planned attempts (229 excluded)
Claude Code – Claude Haiku 5.5 (high)Anthropic$0.010485 of 870 planned attempts

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); Claude Code – Claude Haiku 5.5 (high): 1.1 min (partial coverage)0m0m1m1m1m0.6 minClaude Sonnet 5.5 (medium)1.1 minClaude Haiku 5.5 (high)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Claude Code – Claude Sonnet 5.5 (medium)Anthropic0.6 min568 of 870 planned attempts (229 excluded)
Claude Code – Claude Haiku 5.5 (high)Anthropic1.1 min485 of 870 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Claude Code – Claude Sonnet 5.5 (medium) or Claude Code – Claude Haiku 5.5 (high)?
Claude Code – Claude Sonnet 5.5 (medium), at 77 against 75 for Claude Code – Claude Haiku 5.5 (high). Claude Code – Claude Sonnet 5.5 (medium): 500 of 870 planned attempts (229 excluded). Claude Code – Claude Haiku 5.5 (high): 422 of 870 planned attempts. Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Claude Code – Claude Sonnet 5.5 (medium) or Claude Code – Claude Haiku 5.5 (high)?
Claude Code – Claude Haiku 5.5 (high), at $0.010 against $0.052 for Claude Code – Claude Sonnet 5.5 (medium).
Which is faster per task, Claude Code – Claude Sonnet 5.5 (medium) or Claude Code – Claude Haiku 5.5 (high)?
Claude Code – Claude Sonnet 5.5 (medium), at 0.6 min against 1.1 min for Claude Code – Claude Haiku 5.5 (high).
Which has the larger context window, Claude Code – Claude Sonnet 5.5 (medium) or Claude Code – Claude Haiku 5.5 (high)?
Not known yet: Claude Code – Claude Sonnet 5.5 (medium) has no context window data and Claude Code – Claude Haiku 5.5 (high) has no context window data.

More: Claude Code – Claude Sonnet 5.5 (medium) · Claude Code – Claude Haiku 5.5 (high) · all comparisons