Axis Spatial

Gemini 3.1 Flash-Lite (minimal), Terminus-2 vs. Step 5 Preview (Reasoning), Terminus-2

Gemini 3.1 Flash-Lite (minimal), Terminus-2 against Step 5 Preview (Reasoning), Terminus-2: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.

Side by side

Gemini 3.1 Flash-Lite (minimal), Terminus-2 vs. Step 5 Preview (Reasoning), Terminus-2
MetricGemini 3.1 Flash-Lite (minimal), Terminus-2Step 5 Preview (Reasoning), Terminus-2
Geospatial Agent Index: Text only3234
Geospatial Agent Index: Text + visionNo dataNo data
Earth-Bench V2 score3432
GeoBenchX score4417
GS-QA2 score1852
Vision agents scoreNo dataNo data
GeoAgentBench score (Guided workflows; not in the Agent Index)4250
GeoAnalystBench score (Guided workflows; not in the Agent Index)4253
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 score2735
GIS analysis score1367
Climate and time series score3234
Spatial statistics score00
Making maps score4019
Recognising infeasible requests score6524
Cost per task$0.0066$0.071
Time per task (at 100 output tokens/s)0.6 min7.9 min (estimated)
Tokens per attempt23k90k
Turns per attempt4.911.1
Input price per 1M tokens$0.25$1.00
Output price per 1M tokens$1.50$2.70
Context window1,048,5761,024,000
Image inputYesYes
DeveloperGoogleStepFun

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: Step 5 Preview (Reasoning), Terminus-2: 34; Gemini 3.1 Flash-Lite (minimal), Terminus-2: 32025507510034Step 5 Preview (Reasoning)32Gemini 3.1 Flash-Lite (minimal)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelDeveloperGeospatial Agent Index
Step 5 Preview (Reasoning), Terminus-2StepFun34
Gemini 3.1 Flash-Lite (minimal), Terminus-2Google32

Cost per task

Average cost per task (USD) · Lower is better

Cost per taskCost per task in US dollars: Gemini 3.1 Flash-Lite (minimal), Terminus-2: $0.0066; Step 5 Preview (Reasoning), Terminus-2: $0.071$0$0.02$0.04$0.06$0.08$0.0066Gemini 3.1 Flash-Lite (minimal)$0.071Step 5 Preview (Reasoning)
Data table: Cost per task
Cost per task
ModelDeveloperCost per task
Gemini 3.1 Flash-Lite (minimal), Terminus-2Google$0.0066
Step 5 Preview (Reasoning), Terminus-2StepFun$0.071

Output tokens per task

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

Output tokens per taskOutput tokens per task: Gemini 3.1 Flash-Lite (minimal), Terminus-2: 2k; Step 5 Preview (Reasoning), Terminus-2: 10k05k10k15k20k2kGemini 3.1 Flash-Lite (minimal)10kStep 5 Preview (Reasoning)
Data table: Output tokens per task
Output tokens per task
ModelDeveloperOutput tokens per task
Gemini 3.1 Flash-Lite (minimal), Terminus-2Google2k
Step 5 Preview (Reasoning), Terminus-2StepFun10k

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Gemini 3.1 Flash-Lite (minimal), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Step 5 Preview (Reasoning), Terminus-2, 34 to 32.
Which is cheaper per task, Gemini 3.1 Flash-Lite (minimal), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Gemini 3.1 Flash-Lite (minimal), Terminus-2, $0.0066 to $0.071.
Which writes fewer output tokens per task, Gemini 3.1 Flash-Lite (minimal), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Gemini 3.1 Flash-Lite (minimal), Terminus-2, 2k to 10k.
Which has the larger context window, Gemini 3.1 Flash-Lite (minimal), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Gemini 3.1 Flash-Lite (minimal), Terminus-2, 1,048,576 tokens to 1,024,000 tokens.

More: Gemini 3.1 Flash-Lite (minimal), Terminus-2 · Step 5 Preview (Reasoning), Terminus-2 · All comparisons