Axis Spatial

Nemotron 3 Ultra (high), Terminus-2 vs. GLM-5.3-Flash (max), Claude Code

Nemotron 3 Ultra (high), Terminus-2 against GLM-5.3-Flash (max), Claude Code: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. The harnesses differ, so part of any gap can come from the harness. Methodology.

Side by side

Nemotron 3 Ultra (high), Terminus-2 vs. GLM-5.3-Flash (max), Claude Code
MetricNemotron 3 Ultra (high), Terminus-2GLM-5.3-Flash (max), Claude Code
Geospatial Agent Index: Text only6872
Geospatial Agent Index: Text + visionNo data73
Earth-Bench V2 score6869
GeoBenchX score6570
GS-QA2 score7076
Vision agents scoreNo data78
GeoAgentBench score (Guided workflows; not in the Agent Index)9698
GeoAnalystBench score (Guided workflows; not in the Agent Index)63100
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 score7074
GIS analysis score7079
Climate and time series score6867
Spatial statistics score3178
Making maps score7074
Recognising infeasible requests score6865
Cost per task$0.069$0.093
Time per task (at 100 output tokens/s)2.4 min6.5 min (estimated)
Tokens per attempt148k962k
Turns per attempt12.118.9
Input price per 1M tokens$0.50$0.15
Output price per 1M tokens$2.20$0.50
Context window262,1441,048,576
Image inputNoYes
DeveloperNVIDIAZ.ai

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: GLM-5.3-Flash (max), Claude Code: 72; Nemotron 3 Ultra (high), Terminus-2: 68025507510072GLM-5.3-Flash (max)68Nemotron 3 Ultra (high)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelDeveloperGeospatial Agent Index
GLM-5.3-Flash (max), Claude CodeZ.ai72
Nemotron 3 Ultra (high), Terminus-2NVIDIA68

Cost per task

Average cost per task (USD) · Lower is better

Cost per taskCost per task in US dollars: Nemotron 3 Ultra (high), Terminus-2: $0.069; GLM-5.3-Flash (max), Claude Code: $0.093$0$0.025$0.05$0.075$0.10$0.069Nemotron 3 Ultra (high)$0.093GLM-5.3-Flash (max)
Data table: Cost per task
Cost per task
ModelDeveloperCost per task
Nemotron 3 Ultra (high), Terminus-2NVIDIA$0.069
GLM-5.3-Flash (max), Claude CodeZ.ai$0.093

Output tokens per task

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

Output tokens per taskOutput tokens per task: Nemotron 3 Ultra (high), Terminus-2: 10k; GLM-5.3-Flash (max), Claude Code: 29k010k20k30k40k10kNemotron 3 Ultra (high)29kGLM-5.3-Flash (max)
Data table: Output tokens per task
Output tokens per task
ModelDeveloperOutput tokens per task
Nemotron 3 Ultra (high), Terminus-2NVIDIA10k
GLM-5.3-Flash (max), Claude CodeZ.ai29k

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Nemotron 3 Ultra (high), Terminus-2 or GLM-5.3-Flash (max), Claude Code?
GLM-5.3-Flash (max), Claude Code, 72 to 68.
Which is cheaper per task, Nemotron 3 Ultra (high), Terminus-2 or GLM-5.3-Flash (max), Claude Code?
Nemotron 3 Ultra (high), Terminus-2, $0.069 to $0.093.
Which writes fewer output tokens per task, Nemotron 3 Ultra (high), Terminus-2 or GLM-5.3-Flash (max), Claude Code?
Nemotron 3 Ultra (high), Terminus-2, 10k to 29k.
Which has the larger context window, Nemotron 3 Ultra (high), Terminus-2 or GLM-5.3-Flash (max), Claude Code?
GLM-5.3-Flash (max), Claude Code, 1,048,576 tokens to 262,144 tokens.

More: Nemotron 3 Ultra (high), Terminus-2 · GLM-5.3-Flash (max), Claude Code · All comparisons