Axis Spatial

Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2 vs. Qwen 3.8 27B (xhigh), Terminus-2

Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2 against Qwen 3.8 27B (xhigh), Terminus-2: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.

Side by side

Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2 vs. Qwen 3.8 27B (xhigh), Terminus-2
MetricNemotron 3 Nano Omni 30B (Reasoning), Terminus-2Qwen 3.8 27B (xhigh), Terminus-2
Geospatial Agent Index: Text only2061
Geospatial Agent Index: Text + visionNo dataNo data
Earth-Bench V2 score2944
GeoBenchX score2166
GS-QA2 score974
Vision agents scoreNo dataNo data
GeoAgentBench score (Guided workflows; not in the Agent Index)2660
GeoAnalystBench score (Guided workflows; not in the Agent Index)1689
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 score1764
GIS analysis score677
Climate and time series score2742
Spatial statistics score069
Making maps score1668
Recognising infeasible requests score3357
Cost per task$0.13$0.10
Time per task (at 100 output tokens/s)4.9 min7.3 min
Tokens per attempt589k335k
Turns per attempt30.714.8
Input price per 1M tokens$0.20$0.45
Output price per 1M tokens$0.80$3.20
Context window256,000262,144
Image inputYesYes
DeveloperNVIDIAAlibaba (Qwen)

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: Qwen 3.8 27B (xhigh), Terminus-2: 61; Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2: 20025507510061Qwen 3.8 27B (xhigh)20Nemotron 3 Nano Omni 30B (Reasoning)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelDeveloperGeospatial Agent Index
Qwen 3.8 27B (xhigh), Terminus-2Alibaba (Qwen)61
Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2NVIDIA20

Cost per task

Average cost per task (USD) · Lower is better

Cost per taskCost per task in US dollars: Qwen 3.8 27B (xhigh), Terminus-2: $0.10; Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2: $0.13$0$0.05$0.10$0.15$0.20$0.10Qwen 3.8 27B (xhigh)$0.13Nemotron 3 Nano Omni 30B (Reasoning)
Data table: Cost per task
Cost per task
ModelDeveloperCost per task
Qwen 3.8 27B (xhigh), Terminus-2Alibaba (Qwen)$0.10
Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2NVIDIA$0.13

Output tokens per task

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

Output tokens per taskOutput tokens per task: Qwen 3.8 27B (xhigh), Terminus-2: 19k; Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2: 22k010k20k30k40k19kQwen 3.8 27B (xhigh)22kNemotron 3 Nano Omni 30B (Reasoning)
Data table: Output tokens per task
Output tokens per task
ModelDeveloperOutput tokens per task
Qwen 3.8 27B (xhigh), Terminus-2Alibaba (Qwen)19k
Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2NVIDIA22k

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2 or Qwen 3.8 27B (xhigh), Terminus-2?
Qwen 3.8 27B (xhigh), Terminus-2, 61 to 20.
Which is cheaper per task, Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2 or Qwen 3.8 27B (xhigh), Terminus-2?
Qwen 3.8 27B (xhigh), Terminus-2, $0.10 to $0.13.
Which writes fewer output tokens per task, Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2 or Qwen 3.8 27B (xhigh), Terminus-2?
Qwen 3.8 27B (xhigh), Terminus-2, 19k to 22k.
Which has the larger context window, Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2 or Qwen 3.8 27B (xhigh), Terminus-2?
Qwen 3.8 27B (xhigh), Terminus-2, 262,144 tokens to 256,000 tokens.

More: Nemotron 3 Nano Omni 30B (Reasoning), Terminus-2 · Qwen 3.8 27B (xhigh), Terminus-2 · All comparisons