Terminus-2 – Kimi K3 (always on) vs. Kimi Code – Kimi K2.6 (always on): geospatial agent comparison

Comparison between Terminus-2 – Kimi K3 (always on) and Kimi Code – Kimi K2.6 (always on) on the Geospatial Agent Index, each benchmark, cost, time and token use, from the same tasks, agent and limits. Methodology.

Side by side

Terminus-2 – Kimi K3 (always on) vs. Kimi Code – Kimi K2.6 (always on)
Metric	Terminus-2 – Kimi K3 (always on)	Kimi Code – Kimi K2.6 (always on)
Geospatial Agent Index	58*	56* (partial: attempt 1 on 72 of 320 tasks)
Earth-Bench V2 score	61	55
GeoBenchX score	55	57
GeoAgentBench score (guided GIS workflow; outside the index)	94	No data
GeoAnalystBench score (guided GIS workflow; outside the index)	89	No data
Raster and remote sensing score	59	60
Vector and overlay score	33	0
Networks and routing score	No data	No data
Climate and time series score	66	0
Spatial statistics and interpolation score	50	67
Mapping and cartography score	78	83
Recognising infeasible requests score	38	40
Cost per task	$0.336	$0.219
Time per task	3.9 min	9.7 min
Tokens per attempt	76k	840k
Turns per attempt	7.7	No data
Attempts decided	320	71
Input price per 1M tokens	$3.00	$0.95
Output price per 1M tokens	$15.00	$4.00
Context window	1,000,000	262,144
Image input	Yes	Yes
Developer	Moonshot AI	Moonshot AI

Charts

Partial coverage. Kimi Code – Kimi K2.6 (always on): 11 of 147 Earth-Bench V2 tasks; 61 of 173 GeoBenchX tasks. Grey placeholders identify these entries in the index, cost and time charts; their height does not represent a value. Comparable bars appear when first-attempt coverage is complete. Their available results remain in the side-by-side table.

Geospatial Agent Index

Equal-weight average of the evaluation scores, 0 to 100 · Higher is better

Planned attempts still to come

Data table: Geospatial Agent Index

Geospatial Agent Index
Model	Creator	Geospatial Agent Index	Range while attempts are pending	Benchmarks covered	Coverage (attempts)
Terminus-2 – Kimi K3 (always on)	Moonshot AI	58*	No pending judgements; coverage incomplete; 1 trace review declined by the judge	2 of 2	320 of 614 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

Planned attempts still to come

How to read this chart

Not shown: partial coverage. Kimi Code – Kimi K2.6 (always on).

Data table: Cost per task

Cost per task
Model	Creator	Cost per task	Coverage (attempts)
Terminus-2 – Kimi K3 (always on)	Moonshot AI	$0.336	320 of 614 planned attempts

Time per task

Average agent wall time per task · Lower is better

Planned attempts still to come

How to read this chart

Not shown: partial coverage. Kimi Code – Kimi K2.6 (always on).

Data table: Time per task

Time per task
Model	Creator	Time per task	Coverage (attempts)
Terminus-2 – Kimi K3 (always on)	Moonshot AI	3.9 min	320 of 614 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – Kimi K3 (always on) or Kimi Code – Kimi K2.6 (always on)?

Not comparable yet: Kimi Code – Kimi K2.6 (always on) has partial coverage (11 of 147 Earth-Bench V2 tasks; 61 of 173 GeoBenchX tasks), so it is not ranked. Terminus-2 – Kimi K3 (always on): 320 of 614 planned attempts. Kimi Code – Kimi K2.6 (always on): 71 of 614 planned attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Terminus-2 – Kimi K3 (always on) or Kimi Code – Kimi K2.6 (always on)?

Kimi Code – Kimi K2.6 (always on), at $0.219 against $0.336 for Terminus-2 – Kimi K3 (always on).

Which is faster per task, Terminus-2 – Kimi K3 (always on) or Kimi Code – Kimi K2.6 (always on)?

Terminus-2 – Kimi K3 (always on), at 3.9 min against 9.7 min for Kimi Code – Kimi K2.6 (always on).

Which has the larger context window, Terminus-2 – Kimi K3 (always on) or Kimi Code – Kimi K2.6 (always on)?

Terminus-2 – Kimi K3 (always on), at 1,000,000 tokens against 262,144 tokens for Kimi Code – Kimi K2.6 (always on).

More: Terminus-2 – Kimi K3 (always on) · Kimi Code – Kimi K2.6 (always on) · all comparisons