Axis Spatial

GLM-5.3-Flash (low), Terminus-2 vs. Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2

GLM-5.3-Flash (low), Terminus-2 against Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.

Side by side

GLM-5.3-Flash (low), Terminus-2 vs. Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2
MetricGLM-5.3-Flash (low), Terminus-2Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2
Geospatial Agent Index: Text only6211
Geospatial Agent Index: Text + visionNo dataNo data
Earth-Bench V2 score5316
GeoBenchX score5712
GS-QA2 score764
Vision agents scoreNo dataNo data
GeoAgentBench score (Guided workflows; not in the Agent Index)9410
GeoAnalystBench score (Guided workflows; not in the Agent Index)9532
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 score6711
GIS analysis score757
Climate and time series score5915
Spatial statistics score380
Making maps score677
Recognising infeasible requests score4712
Cost per task$0.048$0.012
Time per task (at 100 output tokens/s)4.2 min4.9 min
Tokens per attempt476k249k
Turns per attempt14.017.3
Input price per 1M tokens$0.15$0.070
Output price per 1M tokens$0.50$0.20
Context window1,048,576262,144
Image inputYesNo
DeveloperZ.aiNVIDIA

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 (low), Terminus-2: 62; Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2: 11025507510062GLM-5.3-Flash (low)11Nemotron 3.5 Lightning 30B (Reasoning)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelDeveloperGeospatial Agent Index
GLM-5.3-Flash (low), Terminus-2Z.ai62
Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2NVIDIA11

Cost per task

Average cost per task (USD) · Lower is better

Cost per taskCost per task in US dollars: Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2: $0.012; GLM-5.3-Flash (low), Terminus-2: $0.048$0$0.015$0.03$0.045$0.06$0.012Nemotron 3.5 Lightning 30B (Reasoning)$0.048GLM-5.3-Flash (low)
Data table: Cost per task
Cost per task
ModelDeveloperCost per task
Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2NVIDIA$0.012
GLM-5.3-Flash (low), Terminus-2Z.ai$0.048

Output tokens per task

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

Output tokens per taskOutput tokens per task: Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2: 6k; GLM-5.3-Flash (low), Terminus-2: 15k05k10k15k20k6kNemotron 3.5 Lightning 30B (Reasoning)15kGLM-5.3-Flash (low)
Data table: Output tokens per task
Output tokens per task
ModelDeveloperOutput tokens per task
Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2NVIDIA6k
GLM-5.3-Flash (low), Terminus-2Z.ai15k

Frequently asked questions

Which scores higher on the Geospatial Agent Index, GLM-5.3-Flash (low), Terminus-2 or Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2?
GLM-5.3-Flash (low), Terminus-2, 62 to 11.
Which is cheaper per task, GLM-5.3-Flash (low), Terminus-2 or Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2?
Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2, $0.012 to $0.048.
Which writes fewer output tokens per task, GLM-5.3-Flash (low), Terminus-2 or Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2?
Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2, 6k to 15k.
Which has the larger context window, GLM-5.3-Flash (low), Terminus-2 or Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2?
GLM-5.3-Flash (low), Terminus-2, 1,048,576 tokens to 262,144 tokens.

More: GLM-5.3-Flash (low), Terminus-2 · Nemotron 3.5 Lightning 30B (Reasoning), Terminus-2 · All comparisons