Axis Spatial

Gemini 3.8 Flash (low), Terminus-2 vs. Step 5 Preview (Reasoning), Terminus-2

Gemini 3.8 Flash (low), 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 3.8 Flash (low), Terminus-2 vs. Step 5 Preview (Reasoning), Terminus-2
MetricGemini 3.8 Flash (low), Terminus-2Step 5 Preview (Reasoning), Terminus-2
Geospatial Agent Index: Text only7134
Geospatial Agent Index: Text + visionNo dataNo data
Earth-Bench V2 score5432
GeoBenchX score7417
GS-QA2 score8652
Vision agents scoreNo dataNo data
GeoAgentBench score (Guided workflows; not in the Agent Index)9850
GeoAnalystBench score (Guided workflows; not in the Agent Index)8953
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 score7335
GIS analysis score8767
Climate and time series score5434
Spatial statistics score620
Making maps score5819
Recognising infeasible requests score10024
Cost per task$0.11$0.071
Time per task (at 100 output tokens/s)1.9 min7.9 min (estimated)
Tokens per attempt314k90k
Turns per attempt19.011.1
Input price per 1M tokens$0.75$1.00
Output price per 1M tokens$3.75$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: Gemini 3.8 Flash (low), Terminus-2: 71; Step 5 Preview (Reasoning), Terminus-2: 34025507510071Gemini 3.8 Flash (low)34Step 5 Preview (Reasoning)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelDeveloperGeospatial Agent Index
Gemini 3.8 Flash (low), Terminus-2Google71
Step 5 Preview (Reasoning), Terminus-2StepFun34

Cost per task

Average cost per task (USD) · Lower is better

Cost per taskCost per task in US dollars: Step 5 Preview (Reasoning), Terminus-2: $0.071; Gemini 3.8 Flash (low), Terminus-2: $0.11$0$0.05$0.10$0.15$0.20$0.071Step 5 Preview (Reasoning)$0.11Gemini 3.8 Flash (low)
Data table: Cost per task
Cost per task
ModelDeveloperCost per task
Step 5 Preview (Reasoning), Terminus-2StepFun$0.071
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: Gemini 3.8 Flash (low), Terminus-2: 8k; Step 5 Preview (Reasoning), Terminus-2: 10k05k10k15k20k8kGemini 3.8 Flash (low)10kStep 5 Preview (Reasoning)
Data table: Output tokens per task
Output tokens per task
ModelDeveloperOutput tokens per task
Gemini 3.8 Flash (low), Terminus-2Google8k
Step 5 Preview (Reasoning), Terminus-2StepFun10k

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Gemini 3.8 Flash (low), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Gemini 3.8 Flash (low), Terminus-2, 71 to 34.
Which is cheaper per task, Gemini 3.8 Flash (low), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Step 5 Preview (Reasoning), Terminus-2, $0.071 to $0.11.
Which writes fewer output tokens per task, Gemini 3.8 Flash (low), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Gemini 3.8 Flash (low), Terminus-2, 8k to 10k.
Which has the larger context window, Gemini 3.8 Flash (low), Terminus-2 or Step 5 Preview (Reasoning), Terminus-2?
Gemini 3.8 Flash (low), Terminus-2, 1,048,576 tokens to 1,024,000 tokens.

More: Gemini 3.8 Flash (low), Terminus-2 · Step 5 Preview (Reasoning), Terminus-2 · All comparisons