Claude Code – GLM-5.2 (max) vs. Kimi Code – Kimi K2.7 Code (always on): geospatial agent comparison

Comparison between Claude Code – GLM-5.2 (max) and Kimi Code – Kimi K2.7 Code (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

Claude Code – GLM-5.2 (max) vs. Kimi Code – Kimi K2.7 Code (always on)
Metric	Claude Code – GLM-5.2 (max)	Kimi Code – Kimi K2.7 Code (always on)
Geospatial Agent Index	53* (partial: attempt 1 on 200 of 565 tasks)	57* (partial: attempt 1 on 289 of 565 tasks)
Earth-Bench V2 score	63	66
GeoBenchX score	42	48
GS-QA2 score	No data	No data
GeoAgentBench score (guided GIS workflow; outside the index)	No data	No data
GeoAnalystBench score (guided GIS workflow; outside the index)	No data	No data
Raster and remote sensing score	62	64
Vector and overlay score	40	40
Networks and routing score	No data	No data
Climate and time series score	67	71
Spatial statistics and interpolation score	No data	17
Mapping and cartography score	No data	81
Recognising infeasible requests score	41	38
Cost per task	$0.437	$0.300
Time per task	7.1 min	10.2 min
Tokens per attempt	827k	995k
Turns per attempt	18.7	No data
Attempts decided	120	236
Input price per 1M tokens	$1.40	$0.95
Output price per 1M tokens	$4.40	$4.00
Context window	262,144	262,144
Image input	No	Yes
Developer	Z.ai	Moonshot AI

Charts

Partial coverage. Claude Code – GLM-5.2 (max): 35 of 147 Earth-Bench V2 tasks; 165 of 173 GeoBenchX tasks; GS-QA2 incomplete; Kimi Code – Kimi K2.7 Code (always on): 116 of 147 Earth-Bench V2 tasks; GS-QA2 being added. Grey placeholders identify these entries in the index, cost and output token 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

Data table: Geospatial Agent Index

Geospatial Agent Index
Model	Creator	Geospatial Agent Index	Range while attempts are pending	Benchmarks covered	Coverage (attempts)

Cost per task

Average cost per task (USD) · Lower is better

How to read this chart

Not shown: partial coverage. Claude Code – GLM-5.2 (max), Kimi Code – Kimi K2.7 Code (always on).

Data table: Cost per task

Cost per task
Model	Creator	Cost per task	Coverage (attempts)

Output tokens per task

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

How to read this chart

Not shown: partial coverage. Claude Code – GLM-5.2 (max), Kimi Code – Kimi K2.7 Code (always on).

Data table: Output tokens per task

Output tokens per task
Model	Creator	Output tokens per task	Coverage (attempts)

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Claude Code – GLM-5.2 (max) or Kimi Code – Kimi K2.7 Code (always on)?

Not comparable yet: Claude Code – GLM-5.2 (max) has partial coverage (35 of 147 Earth-Bench V2 tasks; 165 of 173 GeoBenchX tasks; GS-QA2 incomplete) and Kimi Code – Kimi K2.7 Code (always on) has partial coverage (116 of 147 Earth-Bench V2 tasks; GS-QA2 being added), so it is not ranked. Claude Code – GLM-5.2 (max): 120 of 614 planned attempts (9 excluded). Kimi Code – Kimi K2.7 Code (always on): 236 of 614 planned attempts (1 excluded). Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Claude Code – GLM-5.2 (max) or Kimi Code – Kimi K2.7 Code (always on)?

Kimi Code – Kimi K2.7 Code (always on), at $0.300 against $0.437 for Claude Code – GLM-5.2 (max).

Which writes fewer output tokens per task, Claude Code – GLM-5.2 (max) or Kimi Code – Kimi K2.7 Code (always on)?

Kimi Code – Kimi K2.7 Code (always on), at 19k against 34k for Claude Code – GLM-5.2 (max).

Which has the larger context window, Claude Code – GLM-5.2 (max) or Kimi Code – Kimi K2.7 Code (always on)?

They are level, at 262,144 tokens.

More: Claude Code – GLM-5.2 (max) · Kimi Code – Kimi K2.7 Code (always on) · all comparisons