Axis Spatial

DeepSeek V4 Flash (max), Terminus-2 vs. MiniMax M3.1 Flash (max), Terminus-2

DeepSeek V4 Flash (max), Terminus-2 against MiniMax M3.1 Flash (max), Terminus-2: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.

Side by side

DeepSeek V4 Flash (max), Terminus-2 vs. MiniMax M3.1 Flash (max), Terminus-2
MetricDeepSeek V4 Flash (max), Terminus-2MiniMax M3.1 Flash (max), Terminus-2
Geospatial Agent Index: Text only6951
Geospatial Agent Index: Text + visionNo image inputNo data
Earth-Bench V2 score6639
GeoBenchX score6242
GS-QA2 score8071
Vision agents scoreNo image inputNo data
GeoAgentBench score (Guided workflows; not in the Agent Index)9688
GeoAnalystBench score (Guided workflows; not in the Agent Index)9547
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 score7857
GIS analysis score7577
Climate and time series score6634
Spatial statistics score2325
Making maps score7957
Recognising infeasible requests score5330
Cost per task$0.062$0.017
Time per task (at 100 output tokens/s)5.7 min8.4 min
Tokens per attempt303k254k
Turns per attempt14.413.2
Input price per 1M tokens$0.44$0.15
Output price per 1M tokens$1.32$0.60
Context window1,048,5761,000,000
Image inputNoYes
DeveloperDeepSeekOther

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: DeepSeek V4 Flash (max), Terminus-2: 69; MiniMax M3.1 Flash (max), Terminus-2: 51025507510069DeepSeek V4 Flash (max)51MiniMax M3.1 Flash (max)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelDeveloperGeospatial Agent Index
DeepSeek V4 Flash (max), Terminus-2DeepSeek69
MiniMax M3.1 Flash (max), Terminus-2Other51

Cost per task

Average cost per task (USD) · Lower is better

Cost per taskCost per task in US dollars: MiniMax M3.1 Flash (max), Terminus-2: $0.017; DeepSeek V4 Flash (max), Terminus-2: $0.062$0$0.02$0.04$0.06$0.08$0.017MiniMax M3.1 Flash (max)$0.062DeepSeek V4 Flash (max)
Data table: Cost per task
Cost per task
ModelDeveloperCost per task
MiniMax M3.1 Flash (max), Terminus-2Other$0.017
DeepSeek V4 Flash (max), Terminus-2DeepSeek$0.062

Output tokens per task

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

Output tokens per taskOutput tokens per task: MiniMax M3.1 Flash (max), Terminus-2: 18k; DeepSeek V4 Flash (max), Terminus-2: 29k010k20k30k40k18kMiniMax M3.1 Flash (max)29kDeepSeek V4 Flash (max)
Data table: Output tokens per task
Output tokens per task
ModelDeveloperOutput tokens per task
MiniMax M3.1 Flash (max), Terminus-2Other18k
DeepSeek V4 Flash (max), Terminus-2DeepSeek29k

Frequently asked questions

Which scores higher on the Geospatial Agent Index, DeepSeek V4 Flash (max), Terminus-2 or MiniMax M3.1 Flash (max), Terminus-2?
DeepSeek V4 Flash (max), Terminus-2, 69 to 51.
Which is cheaper per task, DeepSeek V4 Flash (max), Terminus-2 or MiniMax M3.1 Flash (max), Terminus-2?
MiniMax M3.1 Flash (max), Terminus-2, $0.017 to $0.062.
Which writes fewer output tokens per task, DeepSeek V4 Flash (max), Terminus-2 or MiniMax M3.1 Flash (max), Terminus-2?
MiniMax M3.1 Flash (max), Terminus-2, 18k to 29k.
Which has the larger context window, DeepSeek V4 Flash (max), Terminus-2 or MiniMax M3.1 Flash (max), Terminus-2?
DeepSeek V4 Flash (max), Terminus-2, 1,048,576 tokens to 1,000,000 tokens.

More: DeepSeek V4 Flash (max), Terminus-2 · MiniMax M3.1 Flash (max), Terminus-2 · All comparisons