GLM-5.2 (max), Claude Code vs. Claude Haiku 5.5 (low), Claude Code
GLM-5.2 (max), Claude Code against Claude Haiku 5.5 (low), Claude Code: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.
Side by side
| Metric | GLM-5.2 (max), Claude Code | Claude Haiku 5.5 (low), Claude Code |
|---|---|---|
| Geospatial Agent Index: Text only | 73 | 70 |
| Geospatial Agent Index: Text + vision | No image input | 72 |
| Earth-Bench V2 score | 71 | 62 |
| GeoBenchX score | 66 | 73 |
| GS-QA2 score | 83 | 75 |
| Vision agents score | No image input | 77 |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | No data | 92 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | No data | 100 |
| OGD4All score (standalone; in no index) | No data | 95 |
| GeoNatureAgent score (standalone; in no index) | No data | 100 |
| MultiGlobeQA score (standalone; in no index) | No data | 72 |
| GeoAgentEval score (standalone; in no index) | No data | 92 |
| Remote sensing and raster analysis score | 80 | 72 |
| GIS analysis score | 81 | 73 |
| Climate and time series score | 72 | 64 |
| Spatial statistics score | 46 | 38 |
| Making maps score | 84 | 79 |
| Recognising infeasible requests score | 52 | 73 |
| Cost per task | $0.34 | $0.0053 |
| Time per task (at 100 output tokens/s) | 6.3 min | 0.9 min |
| Tokens per attempt | 617k | 181k |
| Turns per attempt | 15.4 | 5.5 |
| Input price per 1M tokens | $1.40 | $0.10 |
| Output price per 1M tokens | $4.40 | $0.50 |
| Context window | 262,144 | 1,000,000 |
| Image input | No | Yes |
| Developer | Z.ai | Anthropic |
Charts
Geospatial Agent Index
Equal average of Earth-Bench V2, GeoBenchX and GS-QA2, 0 to 100 · Higher is better
Data table: Geospatial Agent Index
| Model | Developer | Geospatial Agent Index |
|---|---|---|
| GLM-5.2 (max), Claude Code | Z.ai | 73 |
| Claude Haiku 5.5 (low), Claude Code | Anthropic | 70 |
Cost per task
Average cost per task (USD) · Lower is better
Data table: Cost per task
| Model | Developer | Cost per task |
|---|---|---|
| Claude Haiku 5.5 (low), Claude Code | Anthropic | $0.0053 |
| GLM-5.2 (max), Claude Code | Z.ai | $0.34 |
Output tokens per task
Average output tokens per attempt, reasoning included · Lower is better
Data table: Output tokens per task
| Model | Developer | Output tokens per task |
|---|---|---|
| Claude Haiku 5.5 (low), Claude Code | Anthropic | 3k |
| GLM-5.2 (max), Claude Code | Z.ai | 28k |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, GLM-5.2 (max), Claude Code or Claude Haiku 5.5 (low), Claude Code?
GLM-5.2 (max), Claude Code, 73 to 70.
Which is cheaper per task, GLM-5.2 (max), Claude Code or Claude Haiku 5.5 (low), Claude Code?
Claude Haiku 5.5 (low), Claude Code, $0.0053 to $0.34.
Which writes fewer output tokens per task, GLM-5.2 (max), Claude Code or Claude Haiku 5.5 (low), Claude Code?
Claude Haiku 5.5 (low), Claude Code, 3k to 28k.
Which has the larger context window, GLM-5.2 (max), Claude Code or Claude Haiku 5.5 (low), Claude Code?
Claude Haiku 5.5 (low), Claude Code, 1,000,000 tokens to 262,144 tokens.
More: GLM-5.2 (max), Claude Code · Claude Haiku 5.5 (low), Claude Code · All comparisons