Axis Spatial

GLM-5.3 (max), Claude Code vs. Qwen 3.8 27B (xhigh), Qwen Code

GLM-5.3 (max), Claude Code against Qwen 3.8 27B (xhigh), Qwen Code: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. The harnesses differ, so part of any gap can come from the harness. Methodology.

Side by side

GLM-5.3 (max), Claude Code vs. Qwen 3.8 27B (xhigh), Qwen Code
MetricGLM-5.3 (max), Claude CodeQwen 3.8 27B (xhigh), Qwen Code
Geospatial Agent Index: Text only7368
Geospatial Agent Index: Text + visionNo image inputNot run: Vision agents
Earth-Bench V2 score7468
GeoBenchX score6562
GS-QA2 score8175
Vision agents scoreNo image inputNo data
GeoAgentBench score (Guided workflows; not in the Agent Index)9894
GeoAnalystBench score (Guided workflows; not in the Agent Index)9579
Raster and remote sensing score8076
Vector and overlay score8175
Climate and time series score7661
Spatial statistics and interpolation score3854
Mapping and cartography score7563
Recognising infeasible requests score5860
Cost per task$0.48$0.22
Time per task (at 100 output tokens/s)4.3 min4.7 min (estimated)
Tokens per attempt489k840k
Turns per attempt13.417.6
Attempts scored488488
Input price per 1M tokens$1.40$0.45
Output price per 1M tokens$4.40$3.20
Context window1,048,576262,144
Image inputNoYes
DeveloperZ.aiAlibaba (Qwen)

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: GLM-5.3 (max), Claude Code: 73; Qwen 3.8 27B (xhigh), Qwen Code: 68025507510073GLM-5.3 (max)68Qwen 3.8 27B (xhigh)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelDeveloperGeospatial Agent IndexStatusEvaluations scoredTasks attempted
GLM-5.3 (max), Claude CodeZ.ai73Complete3 of 3488 of 488 tasks
Qwen 3.8 27B (xhigh), Qwen CodeAlibaba (Qwen)68Complete3 of 3488 of 488 tasks

Cost per task

Average cost per task (USD) · Lower is better

Cost per taskCost per task in US dollars: Qwen 3.8 27B (xhigh), Qwen Code: $0.22; GLM-5.3 (max), Claude Code: $0.48$0$0.15$0.30$0.45$0.60$0.22Qwen 3.8 27B (xhigh)$0.48GLM-5.3 (max)
Data table: Cost per task
Cost per task
ModelDeveloperCost per taskTasks attempted
Qwen 3.8 27B (xhigh), Qwen CodeAlibaba (Qwen)$0.22488 of 488 tasks
GLM-5.3 (max), Claude CodeZ.ai$0.48488 of 488 tasks

Output tokens per task

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

Output tokens per taskOutput tokens per task: GLM-5.3 (max), Claude Code: 15k; Qwen 3.8 27B (xhigh), Qwen Code: 28k010k20k30k40k15kGLM-5.3 (max)28kQwen 3.8 27B (xhigh)
Data table: Output tokens per task
Output tokens per task
ModelDeveloperOutput tokens per taskTasks attempted
GLM-5.3 (max), Claude CodeZ.ai15k488 of 488 tasks
Qwen 3.8 27B (xhigh), Qwen CodeAlibaba (Qwen)28k488 of 488 tasks

Frequently asked questions

Which scores higher on the Geospatial Agent Index, GLM-5.3 (max), Claude Code or Qwen 3.8 27B (xhigh), Qwen Code?
GLM-5.3 (max), Claude Code, 73 to 68. Both have attempted all 488 tasks.
Which is cheaper per task, GLM-5.3 (max), Claude Code or Qwen 3.8 27B (xhigh), Qwen Code?
Qwen 3.8 27B (xhigh), Qwen Code, $0.22 to $0.48.
Which writes fewer output tokens per task, GLM-5.3 (max), Claude Code or Qwen 3.8 27B (xhigh), Qwen Code?
GLM-5.3 (max), Claude Code, 15k to 28k.
Which has the larger context window, GLM-5.3 (max), Claude Code or Qwen 3.8 27B (xhigh), Qwen Code?
GLM-5.3 (max), Claude Code, 1,048,576 tokens to 262,144 tokens.

More: GLM-5.3 (max), Claude Code · Qwen 3.8 27B (xhigh), Qwen Code · All comparisons