Axis Spatial

Terminus-2 – DeepSeek V4 Flash (max) vs. Terminus-2 – Gemma 4 26B A4B (thinking on): geospatial agent comparison

Comparison between Terminus-2 – DeepSeek V4 Flash (max) and Terminus-2 – Gemma 4 26B A4B (thinking on) 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. Terminus-2 – Gemma 4 26B A4B (thinking on)
MetricTerminus-2 – DeepSeek V4 Flash (max)Terminus-2 – Gemma 4 26B A4B (thinking on)
Geospatial Agent Index74* (partial: 1.1 of 3 attempts)62
GeoAgentBench score9887
GeoBenchX score5353
Earth-Bench score4634
GeoAnalystBench score10072
Raster and remote sensing score7057
Vector and overlay score7274
Networks and routing score10087
Climate and time series score7350
Spatial statistics and interpolation score5657
Mapping and cartography score7571
Recognising infeasible requests score4143
Cost per task$0.067$0.016
Time per task9.1 min7.0 min
Tokens per attempt280k127k
Turns per attempt13.29.9
Attempts decided321870
Input price per 1M tokens$0.44$0.10
Output price per 1M tokens$1.32$0.30
Context window1,048,576256,000
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 (max): 74* (partial coverage); Terminus-2 – Gemma 4 26B A4B (thinking on): 62025507510074*DeepSeek V4 Flash (max)62Gemma 4 26B A4B (thinking on)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Terminus-2 – DeepSeek V4 Flash (max)DeepSeek74* (partial: 1.1 of 3 attempts)73 to 744 of 4321 of 870 planned attempts
Terminus-2 – Gemma 4 26B A4B (thinking on)Google62No pending judgements4 of 4870 of 870 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskTerminus-2 – Gemma 4 26B A4B (thinking on): $0.016; Terminus-2 – DeepSeek V4 Flash (max): $0.067 (partial coverage)$0$0.020$0.040$0.060$0.080$0.016Gemma 4 26B A4B (thinking on)$0.067DeepSeek V4 Flash (max)
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
Terminus-2 – Gemma 4 26B A4B (thinking on)Google$0.016870 of 870 planned attempts

Time per task

Average agent wall time per task · Lower is better

  • Partial coverage
Time per taskTerminus-2 – Gemma 4 26B A4B (thinking on): 7.0 min; Terminus-2 – DeepSeek V4 Flash (max): 9.1 min (partial coverage)0m2m5m8m10m7.0 minGemma 4 26B A4B (thinking on)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
Terminus-2 – Gemma 4 26B A4B (thinking on)Google7.0 min870 of 870 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – DeepSeek V4 Flash (max) or Terminus-2 – Gemma 4 26B A4B (thinking on)?
Terminus-2 – DeepSeek V4 Flash (max), at 74 against 62 for Terminus-2 – Gemma 4 26B A4B (thinking on). Terminus-2 – DeepSeek V4 Flash (max): 321 of 870 planned attempts. Terminus-2 – Gemma 4 26B A4B (thinking on): 870 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 Terminus-2 – Gemma 4 26B A4B (thinking on)?
Terminus-2 – Gemma 4 26B A4B (thinking on), at $0.016 against $0.067 for Terminus-2 – DeepSeek V4 Flash (max).
Which is faster per task, Terminus-2 – DeepSeek V4 Flash (max) or Terminus-2 – Gemma 4 26B A4B (thinking on)?
Terminus-2 – Gemma 4 26B A4B (thinking on), at 7.0 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 Terminus-2 – Gemma 4 26B A4B (thinking on)?
Terminus-2 – DeepSeek V4 Flash (max), at 1,048,576 tokens against 256,000 tokens for Terminus-2 – Gemma 4 26B A4B (thinking on).

More: Terminus-2 – DeepSeek V4 Flash (max) · Terminus-2 – Gemma 4 26B A4B (thinking on) · all comparisons