Axis Spatial

Terminus-2 – DeepSeek V4 Flash (high) vs. Terminus-2 – Gemini 3.8 Flash (low): geospatial agent comparison

Comparison between Terminus-2 – DeepSeek V4 Flash (high) and Terminus-2 – Gemini 3.8 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 – DeepSeek V4 Flash (high) vs. Terminus-2 – Gemini 3.8 Flash (low)
MetricTerminus-2 – DeepSeek V4 Flash (high)Terminus-2 – Gemini 3.8 Flash (low)
Geospatial Agent Index72* (attempts per task: 3.2)64* (attempts per task: 2.9)
GeoAgentBench score9496
GeoBenchX score5061
Earth-Bench score4437
GeoAnalystBench score10063
Raster and remote sensing score6062
Vector and overlay score6763
Networks and routing score100100
Climate and time series score5251
Spatial statistics and interpolation score4243
Mapping and cartography score7153
Recognising infeasible requests score4383
Cost per task$0.070$0.115
Time per task10.0 min2.7 min
Tokens per attempt336k314k
Turns per attempt14.717.9
Attempts decided368833
Input price per 1M tokens$0.44$0.75
Output price per 1M tokens$1.32$3.75
Context window1,048,5761,048,576
Image inputNoYes
DeveloperDeepSeekGoogle

Charts

Geospatial Agent Index

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

  • Partial coverage
Geospatial Agent IndexTerminus-2 – DeepSeek V4 Flash (high): 72* (partial coverage); Terminus-2 – Gemini 3.8 Flash (low): 64* (partial coverage)025507510072*DeepSeek V4 Flash (high)64*Gemini 3.8 Flash (low)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Terminus-2 – DeepSeek V4 Flash (high)DeepSeek72* (attempts per task: 3.2)30 to 844 of 4368 of 1,167 planned attempts (21 excluded)
Terminus-2 – Gemini 3.8 Flash (low)Google64* (attempts per task: 2.9)No pending judgements; coverage incomplete4 of 4833 of 1,167 planned attempts (74 excluded)

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskTerminus-2 – DeepSeek V4 Flash (high): $0.070 (partial coverage); Terminus-2 – Gemini 3.8 Flash (low): $0.115 (partial coverage)$0$0.030$0.060$0.090$0.120$0.070DeepSeek V4 Flash (high)$0.115Gemini 3.8 Flash (low)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – DeepSeek V4 Flash (high)DeepSeek$0.070924 of 1,167 planned attempts (21 excluded)
Terminus-2 – Gemini 3.8 Flash (low)Google$0.115833 of 1,167 planned attempts (74 excluded)

Time per task

Average agent wall time per task · Lower is better

  • Partial coverage
Time per taskTerminus-2 – Gemini 3.8 Flash (low): 2.7 min (partial coverage); Terminus-2 – DeepSeek V4 Flash (high): 10.0 min (partial coverage)0m3m7m10m13m2.7 minGemini 3.8 Flash (low)10.0 minDeepSeek V4 Flash (high)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Terminus-2 – DeepSeek V4 Flash (high)DeepSeek10.0 min924 of 1,167 planned attempts (21 excluded)
Terminus-2 – Gemini 3.8 Flash (low)Google2.7 min833 of 1,167 planned attempts (74 excluded)

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – DeepSeek V4 Flash (high) or Terminus-2 – Gemini 3.8 Flash (low)?
Terminus-2 – DeepSeek V4 Flash (high), at 72 against 64 for Terminus-2 – Gemini 3.8 Flash (low). Terminus-2 – DeepSeek V4 Flash (high): 368 of 1,167 planned attempts (21 excluded). Terminus-2 – Gemini 3.8 Flash (low): 833 of 1,167 planned attempts (74 excluded). Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – DeepSeek V4 Flash (high) or Terminus-2 – Gemini 3.8 Flash (low)?
Terminus-2 – DeepSeek V4 Flash (high), at $0.070 against $0.115 for Terminus-2 – Gemini 3.8 Flash (low).
Which is faster per task, Terminus-2 – DeepSeek V4 Flash (high) or Terminus-2 – Gemini 3.8 Flash (low)?
Terminus-2 – Gemini 3.8 Flash (low), at 2.7 min against 10.0 min for Terminus-2 – DeepSeek V4 Flash (high).
Which has the larger context window, Terminus-2 – DeepSeek V4 Flash (high) or Terminus-2 – Gemini 3.8 Flash (low)?
They are level, at 1,048,576 tokens.

More: Terminus-2 – DeepSeek V4 Flash (high) · Terminus-2 – Gemini 3.8 Flash (low) · all comparisons