Terminus-2 – Llama 3.3 70B (Non-reasoning) vs. Claude Code – GLM-5.3 (max, default): geospatial agent comparison

Comparison between Terminus-2 – Llama 3.3 70B (Non-reasoning) and Claude Code – GLM-5.3 (max, default) 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 – Llama 3.3 70B (Non-reasoning) vs. Claude Code – GLM-5.3 (max, default)
Metric	Terminus-2 – Llama 3.3 70B (Non-reasoning)	Claude Code – GLM-5.3 (max, default)
Geospatial Agent Index	8*	64* (partial: attempt 1 on 117 of 565 tasks)
Earth-Bench V2 score	7	76
GeoBenchX score	6	52
GS-QA2 score	10	No data
GeoAgentBench score (guided GIS workflow; outside the index)	8	No data
GeoAnalystBench score (guided GIS workflow; outside the index)	0	No data
Raster and remote sensing score	6	68
Vector and overlay score	11	67
Networks and routing score	No data	No data
Climate and time series score	10	100
Spatial statistics and interpolation score	0	33
Mapping and cartography score	2	69
Recognising infeasible requests score	13	40
Cost per task	$0.022	$0.597
Time per task	3.0 min	10.7 min
Tokens per attempt	59k	627k
Turns per attempt	14.0	16.2
Attempts decided	565	110
Input price per 1M tokens	$0.29	$1.40
Output price per 1M tokens	$2.25	$4.40
Context window	24,000	1,048,576
Image input	No	No
Developer	Meta	Z.ai

Charts

Partial coverage. Claude Code – GLM-5.3 (max, default): 21 of 147 Earth-Bench V2 tasks; 96 of 173 GeoBenchX tasks; GS-QA2 incomplete. 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

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 – Llama 3.3 70B (Non-reasoning)	Meta	8*	No pending judgements; coverage incomplete; 24 results awaiting review	3 of 3	565 of 859 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. Claude Code – GLM-5.3 (max, default).

Data table: Cost per task

Cost per task
Model	Creator	Cost per task	Coverage (attempts)
Terminus-2 – Llama 3.3 70B (Non-reasoning)	Meta	$0.022	565 of 859 planned attempts

Output tokens per task

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

Planned attempts still to come

How to read this chart

Not shown: partial coverage. Claude Code – GLM-5.3 (max, default).

Data table: Output tokens per task

Output tokens per task
Model	Creator	Output tokens per task	Coverage (attempts)
Terminus-2 – Llama 3.3 70B (Non-reasoning)	Meta	2k	565 of 859 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – Llama 3.3 70B (Non-reasoning) or Claude Code – GLM-5.3 (max, default)?

Not comparable yet: Claude Code – GLM-5.3 (max, default) has partial coverage (21 of 147 Earth-Bench V2 tasks; 96 of 173 GeoBenchX tasks; GS-QA2 incomplete), so it is not ranked. Terminus-2 – Llama 3.3 70B (Non-reasoning): 565 of 859 planned attempts. Claude Code – GLM-5.3 (max, default): 110 of 614 planned attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Terminus-2 – Llama 3.3 70B (Non-reasoning) or Claude Code – GLM-5.3 (max, default)?

Terminus-2 – Llama 3.3 70B (Non-reasoning), at $0.022 against $0.597 for Claude Code – GLM-5.3 (max, default).

Which writes fewer output tokens per task, Terminus-2 – Llama 3.3 70B (Non-reasoning) or Claude Code – GLM-5.3 (max, default)?

Terminus-2 – Llama 3.3 70B (Non-reasoning), at 2k against 19k for Claude Code – GLM-5.3 (max, default).

Which has the larger context window, Terminus-2 – Llama 3.3 70B (Non-reasoning) or Claude Code – GLM-5.3 (max, default)?

Claude Code – GLM-5.3 (max, default), at 1,048,576 tokens against 24,000 tokens for Terminus-2 – Llama 3.3 70B (Non-reasoning).

More: Terminus-2 – Llama 3.3 70B (Non-reasoning) · Claude Code – GLM-5.3 (max, default) · all comparisons