Axis Spatial

Gemini 3.8 Flash (low), Terminus-2 vs. Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2

Gemini 3.8 Flash (low), Terminus-2 against Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.

Side by side

Gemini 3.8 Flash (low), Terminus-2 vs. Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2
MetricGemini 3.8 Flash (low), Terminus-2Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2
Geospatial Agent Index: Text only7152
Geospatial Agent Index: Text + visionNo dataNo data
Earth-Bench V2 score5446
GeoBenchX score7453
GS-QA2 score8659
Vision agents scoreNo dataNo data
GeoAgentBench score (Guided workflows; not in the Agent Index)9868
GeoAnalystBench score (Guided workflows; not in the Agent Index)8937
OGD4All score (standalone; in no index)No dataNo data
GeoNatureAgent score (standalone; in no index)No dataNo data
MultiGlobeQA score (standalone; in no index)No dataNo data
GeoAgentEval score (standalone; in no index)No dataNo data
Remote sensing and raster analysis score7361
GIS analysis score8751
Climate and time series score5446
Spatial statistics score6231
Making maps score5867
Recognising infeasible requests score10043
Cost per task$0.11$0.0096
Time per task (at 100 output tokens/s)1.9 min3.8 min
Tokens per attempt314k98k
Turns per attempt19.010.1
Input price per 1M tokens$0.75$0.15
Output price per 1M tokens$3.75$0.50
Context window1,048,576262,144
Image inputYesYes
DeveloperGoogleNVIDIA

Charts

Geospatial Agent Index

Equal average of Earth-Bench V2, GeoBenchX and GS-QA2, 0 to 100 · Higher is better

Geospatial Agent IndexScores 0 to 100: Gemini 3.8 Flash (low), Terminus-2: 71; Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2: 52025507510071Gemini 3.8 Flash (low)52Nemotron 3.5 Super VL 120B (Reasoning)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelDeveloperGeospatial Agent Index
Gemini 3.8 Flash (low), Terminus-2Google71
Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2NVIDIA52

Cost per task

Average cost per task (USD) · Lower is better

Cost per taskCost per task in US dollars: Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2: $0.0096; Gemini 3.8 Flash (low), Terminus-2: $0.11$0$0.05$0.10$0.15$0.20$0.0096Nemotron 3.5 Super VL 120B (Reasoning)$0.11Gemini 3.8 Flash (low)
Data table: Cost per task
Cost per task
ModelDeveloperCost per task
Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2NVIDIA$0.0096
Gemini 3.8 Flash (low), Terminus-2Google$0.11

Output tokens per task

Average output tokens per attempt, reasoning included · Lower is better

Output tokens per taskOutput tokens per task: Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2: 7k; Gemini 3.8 Flash (low), Terminus-2: 8k02k4k6k8k7kNemotron 3.5 Super VL 120B (Reasoning)8kGemini 3.8 Flash (low)
Data table: Output tokens per task
Output tokens per task
ModelDeveloperOutput tokens per task
Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2NVIDIA7k
Gemini 3.8 Flash (low), Terminus-2Google8k

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Gemini 3.8 Flash (low), Terminus-2 or Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2?
Gemini 3.8 Flash (low), Terminus-2, 71 to 52.
Which is cheaper per task, Gemini 3.8 Flash (low), Terminus-2 or Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2?
Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2, $0.0096 to $0.11.
Which writes fewer output tokens per task, Gemini 3.8 Flash (low), Terminus-2 or Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2?
Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2, 7k to 8k.
Which has the larger context window, Gemini 3.8 Flash (low), Terminus-2 or Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2?
Gemini 3.8 Flash (low), Terminus-2, 1,048,576 tokens to 262,144 tokens.

More: Gemini 3.8 Flash (low), Terminus-2 · Nemotron 3.5 Super VL 120B (Reasoning), Terminus-2 · All comparisons