Claude Haiku 5.5 (low), Claude Code vs. Claude Opus 5 (high), Claude Code
Claude Haiku 5.5 (low), Claude Code against Claude Opus 5 (high), Claude Code: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.
Side by side
| Metric | Claude Haiku 5.5 (low), Claude Code | Claude Opus 5 (high), Claude Code |
|---|---|---|
| Geospatial Agent Index: Text only | 70 | 80 |
| Geospatial Agent Index: Text + vision | 72 | 81 |
| Earth-Bench V2 score | 62 | 74 |
| GeoBenchX score | 73 | 75 |
| GS-QA2 score | 75 | 91 |
| Vision agents score | 77 | 86 |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 92 | 100 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 100 | 89 |
| OGD4All score (standalone; in no index) | 95 | 95 |
| GeoNatureAgent score (standalone; in no index) | 100 | 100 |
| MultiGlobeQA score (standalone; in no index) | 72 | 79 |
| GeoAgentEval score (standalone; in no index) | 92 | 96 |
| Remote sensing and raster analysis score | 72 | 83 |
| GIS analysis score | 73 | 88 |
| Climate and time series score | 64 | 78 |
| Spatial statistics score | 38 | 46 |
| Making maps score | 79 | 82 |
| Recognising infeasible requests score | 73 | 78 |
| Cost per task | $0.0053 | $0.32 |
| Time per task (at 100 output tokens/s) | 0.9 min | 1.1 min |
| Tokens per attempt | 181k | 173k |
| Turns per attempt | 5.5 | 7.2 |
| Input price per 1M tokens | $0.10 | $5.00 |
| Output price per 1M tokens | $0.50 | $25.00 |
| Context window | 1,000,000 | 1,000,000 |
| Image input | Yes | Yes |
| Developer | Anthropic | 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 |
|---|---|---|
| Claude Opus 5 (high), Claude Code | Anthropic | 80 |
| 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 |
| Claude Opus 5 (high), Claude Code | Anthropic | $0.32 |
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 |
| Claude Opus 5 (high), Claude Code | Anthropic | 4k |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, Claude Haiku 5.5 (low), Claude Code or Claude Opus 5 (high), Claude Code?
Claude Opus 5 (high), Claude Code, 80 to 70.
Which is cheaper per task, Claude Haiku 5.5 (low), Claude Code or Claude Opus 5 (high), Claude Code?
Claude Haiku 5.5 (low), Claude Code, $0.0053 to $0.32.
Which writes fewer output tokens per task, Claude Haiku 5.5 (low), Claude Code or Claude Opus 5 (high), Claude Code?
Claude Haiku 5.5 (low), Claude Code, 3k to 4k.
Which has the larger context window, Claude Haiku 5.5 (low), Claude Code or Claude Opus 5 (high), Claude Code?
They are level, at 1,000,000 tokens.
More: Claude Haiku 5.5 (low), Claude Code · Claude Opus 5 (high), Claude Code · All comparisons