Axis Spatial

Mistral Large 3 (Non-reasoning), Terminus-2 vs. Nemotron 3 Ultra (high), Terminus-2

Mistral Large 3 (Non-reasoning), Terminus-2 against Nemotron 3 Ultra (high), Terminus-2: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.

Side by side

Mistral Large 3 (Non-reasoning), Terminus-2 vs. Nemotron 3 Ultra (high), Terminus-2
MetricMistral Large 3 (Non-reasoning), Terminus-2Nemotron 3 Ultra (high), Terminus-2
Geospatial Agent Index: Text only3368
Geospatial Agent Index: Text + visionNo dataNo data
Earth-Bench V2 score3168
GeoBenchX score2965
GS-QA2 score3970
Vision agents scoreNo dataNo data
GeoAgentBench score (Guided workflows; not in the Agent Index)4696
GeoAnalystBench score (Guided workflows; not in the Agent Index)4763
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 score2970
GIS analysis score4270
Climate and time series score3468
Spatial statistics score831
Making maps score3370
Recognising infeasible requests score3368
Cost per task$0.026$0.069
Time per task (at 100 output tokens/s)1.1 min2.4 min
Tokens per attempt42k148k
Turns per attempt5.212.1
Input price per 1M tokens$0.50$0.50
Output price per 1M tokens$1.50$2.20
Context window256,000262,144
Image inputYesNo
DeveloperMistral 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: Nemotron 3 Ultra (high), Terminus-2: 68; Mistral Large 3 (Non-reasoning), Terminus-2: 33025507510068Nemotron 3 Ultra (high)33Mistral Large 3 (Non-reasoning)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelDeveloperGeospatial Agent Index
Nemotron 3 Ultra (high), Terminus-2NVIDIA68
Mistral Large 3 (Non-reasoning), Terminus-2Mistral AI33

Cost per task

Average cost per task (USD) · Lower is better

Cost per taskCost per task in US dollars: Mistral Large 3 (Non-reasoning), Terminus-2: $0.026; Nemotron 3 Ultra (high), Terminus-2: $0.069$0$0.02$0.04$0.06$0.08$0.026Mistral Large 3 (Non-reasoning)$0.069Nemotron 3 Ultra (high)
Data table: Cost per task
Cost per task
ModelDeveloperCost per task
Mistral Large 3 (Non-reasoning), Terminus-2Mistral AI$0.026
Nemotron 3 Ultra (high), Terminus-2NVIDIA$0.069

Output tokens per task

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

Output tokens per taskOutput tokens per task: Mistral Large 3 (Non-reasoning), Terminus-2: 4k; Nemotron 3 Ultra (high), Terminus-2: 10k02k5k8k10k4kMistral Large 3 (Non-reasoning)10kNemotron 3 Ultra (high)
Data table: Output tokens per task
Output tokens per task
ModelDeveloperOutput tokens per task
Mistral Large 3 (Non-reasoning), Terminus-2Mistral AI4k
Nemotron 3 Ultra (high), Terminus-2NVIDIA10k

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Mistral Large 3 (Non-reasoning), Terminus-2 or Nemotron 3 Ultra (high), Terminus-2?
Nemotron 3 Ultra (high), Terminus-2, 68 to 33.
Which is cheaper per task, Mistral Large 3 (Non-reasoning), Terminus-2 or Nemotron 3 Ultra (high), Terminus-2?
Mistral Large 3 (Non-reasoning), Terminus-2, $0.026 to $0.069.
Which writes fewer output tokens per task, Mistral Large 3 (Non-reasoning), Terminus-2 or Nemotron 3 Ultra (high), Terminus-2?
Mistral Large 3 (Non-reasoning), Terminus-2, 4k to 10k.
Which has the larger context window, Mistral Large 3 (Non-reasoning), Terminus-2 or Nemotron 3 Ultra (high), Terminus-2?
Nemotron 3 Ultra (high), Terminus-2, 262,144 tokens to 256,000 tokens.

More: Mistral Large 3 (Non-reasoning), Terminus-2 · Nemotron 3 Ultra (high), Terminus-2 · All comparisons