Claude Sonnet 5.5 (xhigh) vs Claude Sonnet 5.5 (max)
Results updated 3 November 2026 · Both in Claude Code · How we benchmark
Verdict
Not comparable yet: Claude Sonnet 5.5 (max) is not yet ranked.
- Cost per task
- $0.11 vs $0.54
- Time per task
- 1.2 min vs 5.6 min (estimated)
- Tokens per attempt
- 158k vs 649k
- Image input
- Yes vs Yes
Claude Sonnet 5.5 (xhigh), Claude Code scores higher on Earth-Bench V2 and GeoBenchX; Claude Sonnet 5.5 (max), Claude Code scores higher on GS-QA2; they are level on Vision agents. Claude Sonnet 5.5 (xhigh), Claude Code is cheaper and faster: $0.11 against $0.54 per task, and 1.2 min against 5.6 min.
Not yet ranked. Claude Sonnet 5.5 (max), Claude Code. Not in the Agent Index, cost and time charts until it has a score on every index evaluation. Results so far are in the side-by-side table.
Where they differ most
By kind of work, share of tasks passed, 0 to 100 · Higher is better
| Kind of work | Claude Sonnet 5.5 (xhigh) | Claude Sonnet 5.5 (max) |
|---|---|---|
| Spatial statistics | 46 | 100 |
| Making maps | 88 | 78 |
| Recognising infeasible requests | 83 | 75 |
| Climate and time series | 66 | 58 |
Where the tasks are set: each kind of work links to its tasks and scoresCharts for each: Claude Sonnet 5.5 (xhigh), Claude Code · Claude Sonnet 5.5 (max), Claude Code.
Side by side
| Metric | Claude Sonnet 5.5 (xhigh), Claude Code | Claude Sonnet 5.5 (max), Claude Code |
|---|---|---|
| Geospatial Agent Index: Text only | 79 | 75 |
| Geospatial Agent Index: Text + vision | 82 | No data |
| Earth-Bench V2 score | 68 | 57 |
| GeoBenchX score | 81 | 77 |
| GS-QA2 score | 87 | 92 |
| Vision agents score | 89 | 89 |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 98 | 100 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 95 | 100 |
| OGD4All score (standalone; in no index) | 97 | 97 |
| GeoNatureAgent score (standalone; in no index) | 100 | 100 |
| MultiGlobeQA score (standalone; in no index) | 79 | 78 |
| GeoAgentEval score (standalone; in no index) | 100 | 100 |
| Remote sensing and raster analysis score | 81 | 88 |
| GIS analysis score | 89 | 95 |
| Climate and time series score | 66 | 58 |
| Spatial statistics score | 46 | 100 |
| Making maps score | 88 | 78 |
| Recognising infeasible requests score | 83 | 75 |
| Cost per task | $0.11 | $0.54 |
| Time per task (at 100 output tokens/s) | 1.2 min | 5.6 min (estimated) |
| Tokens per attempt | 158k | 649k |
| Turns per attempt | 6.6 | 12.8 |
| Input price per 1M tokens | $2.00 | $2.00 |
| Output price per 1M tokens | $10.00 | $10.00 |
| Context window | 1,000,000 | 1,000,000 |
| Image input | Yes | Yes |
| Developer | Anthropic | Anthropic |