Axis Spatial

Terminus-2 – DeepSeek V4 Flash (max) vs. Claude Code – Claude Opus 5.5 (high): geospatial agent comparison

Comparison between Terminus-2 – DeepSeek V4 Flash (max) and Claude Code – Claude Opus 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

Terminus-2 – DeepSeek V4 Flash (max) vs. Claude Code – Claude Opus 5.5 (high)
MetricTerminus-2 – DeepSeek V4 Flash (max)Claude Code – Claude Opus 5.5 (high)
Geospatial Agent Index74* (partial: 1.1 of 3 attempts)83* (partial: 1.7 of 3 attempts)
GeoAgentBench score9896
GeoBenchX score5366
Earth-Bench score4669
GeoAnalystBench score100100
Raster and remote sensing score7084
Vector and overlay score7283
Networks and routing score100100
Climate and time series score7379
Spatial statistics and interpolation score5662
Mapping and cartography score7576
Recognising infeasible requests score4159
Cost per task$0.067$0.175
Time per task9.1 min1.0 min
Tokens per attempt280k127k
Turns per attempt13.25.7
Attempts decided321422
Input price per 1M tokens$0.44$4.00
Output price per 1M tokens$1.32$20.00
Context window1,048,576No data
Image inputNoNo data
DeveloperDeepSeekAnthropic

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 (high): 83* (partial coverage); Terminus-2 – DeepSeek V4 Flash (max): 74* (partial coverage)025507510083*Claude Opus 5.5 (high)74*DeepSeek V4 Flash (max)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Claude Code – Claude Opus 5.5 (high)Anthropic83* (partial: 1.7 of 3 attempts)71 to 834 of 4422 of 870 planned attempts
Terminus-2 – DeepSeek V4 Flash (max)DeepSeek74* (partial: 1.1 of 3 attempts)73 to 744 of 4321 of 870 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskTerminus-2 – DeepSeek V4 Flash (max): $0.067 (partial coverage); Claude Code – Claude Opus 5.5 (high): $0.175 (partial coverage)$0$0.050$0.100$0.150$0.200$0.067DeepSeek V4 Flash (max)$0.175Claude Opus 5.5 (high)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – DeepSeek V4 Flash (max)DeepSeek$0.067329 of 870 planned attempts
Claude Code – Claude Opus 5.5 (high)Anthropic$0.175496 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 (high): 1.0 min (partial coverage); Terminus-2 – DeepSeek V4 Flash (max): 9.1 min (partial coverage)0m2m5m8m10m1.0 minClaude Opus 5.5 (high)9.1 minDeepSeek V4 Flash (max)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Terminus-2 – DeepSeek V4 Flash (max)DeepSeek9.1 min329 of 870 planned attempts
Claude Code – Claude Opus 5.5 (high)Anthropic1.0 min496 of 870 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – DeepSeek V4 Flash (max) or Claude Code – Claude Opus 5.5 (high)?
Claude Code – Claude Opus 5.5 (high), at 83 against 74 for Terminus-2 – DeepSeek V4 Flash (max). Terminus-2 – DeepSeek V4 Flash (max): 321 of 870 planned attempts. Claude Code – Claude Opus 5.5 (high): 422 of 870 planned attempts. Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – DeepSeek V4 Flash (max) or Claude Code – Claude Opus 5.5 (high)?
Terminus-2 – DeepSeek V4 Flash (max), at $0.067 against $0.175 for Claude Code – Claude Opus 5.5 (high).
Which is faster per task, Terminus-2 – DeepSeek V4 Flash (max) or Claude Code – Claude Opus 5.5 (high)?
Claude Code – Claude Opus 5.5 (high), at 1.0 min against 9.1 min for Terminus-2 – DeepSeek V4 Flash (max).
Which has the larger context window, Terminus-2 – DeepSeek V4 Flash (max) or Claude Code – Claude Opus 5.5 (high)?
Not known yet: Claude Code – Claude Opus 5.5 (high) has no context window data.

More: Terminus-2 – DeepSeek V4 Flash (max) · Claude Code – Claude Opus 5.5 (high) · all comparisons