Claude Fable 5.1 (medium) vs Claude Fable 5.1 (high)
Results updated 3 November 2026 · Both in Claude Code · How we benchmark
Verdict
Claude Fable 5.1 (medium) edges Claude Fable 5.1 (high) by 1 point, and is cheaper and faster.
- Cost per task
- $0.33 vs $0.44
- Time per task
- 0.8 min vs 1.1 min
- Tokens per attempt
- 107k vs 132k
- Image input
- No data vs No data
Claude Fable 5.1 (medium), Claude Code scores higher on Earth-Bench V2 and GeoBenchX; Claude Fable 5.1 (high), Claude Code scores higher on GS-QA2 and Vision agents. Claude Fable 5.1 (medium), Claude Code is cheaper and faster: $0.33 against $0.44 per task, and 0.8 min against 1.1 min.
Where they differ most
By kind of work, share of tasks passed, 0 to 100 · Higher is better
| Kind of work | Claude Fable 5.1 (medium) | Claude Fable 5.1 (high) |
|---|---|---|
| Change detection | 72 | 64 |
| Making maps | 84 | 79 |
| Climate and time series | 74 | 76 |
| GIS analysis | 86 | 88 |
Where the tasks are set: each kind of work links to its tasks and scoresCharts for each: Claude Fable 5.1 (medium), Claude Code · Claude Fable 5.1 (high), Claude Code.
Side by side
| Metric | Claude Fable 5.1 (medium), Claude Code | Claude Fable 5.1 (high), Claude Code |
|---|---|---|
| Geospatial Agent Index: Text only | 81 | 80 |
| Geospatial Agent Index: Text + vision | 81 | 82 |
| Earth-Bench V2 score | 73 | 72 |
| GeoBenchX score | 81 | 80 |
| GS-QA2 score | 89 | 90 |
| Vision agents score | 81 | 88 |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 100 | 100 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 100 | 95 |
| OGD4All score (standalone; in no index) | 97 | 97 |
| GeoNatureAgent score (standalone; in no index) | 100 | 100 |
| MultiGlobeQA score (standalone; in no index) | 78 | 79 |
| GeoAgentEval score (standalone; in no index) | 96 | 100 |
| ImpactMesh score (standalone; in no index) | No data | No data |
| Remote sensing and raster analysis score | 87 | 87 |
| Change detection score | 72 | 64 |
| GIS analysis score | 86 | 88 |
| Climate and time series score | 74 | 76 |
| Making maps score | 84 | 79 |
| Cost per task | $0.33 | $0.44 |
| Time per task (at 100 output tokens/s) | 0.8 min | 1.1 min |
| Tokens per attempt | 107k | 132k |
| Turns per attempt | 4.9 | 5.4 |
| Input price per 1M tokens | $10.00 | $10.00 |
| Output price per 1M tokens | $50.00 | $50.00 |
| Context window | 200,000 | 200,000 |
| Developer | Anthropic | Anthropic |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, Claude Fable 5.1 (medium), Claude Code or Claude Fable 5.1 (high), Claude Code?
Claude Fable 5.1 (medium), Claude Code, 81 to 80.
Which is cheaper per task, Claude Fable 5.1 (medium), Claude Code or Claude Fable 5.1 (high), Claude Code?
Claude Fable 5.1 (medium), Claude Code, $0.33 to $0.44.
Which writes fewer output tokens per task, Claude Fable 5.1 (medium), Claude Code or Claude Fable 5.1 (high), Claude Code?
Claude Fable 5.1 (medium), Claude Code, 2k to 3k.
Which has the larger context window, Claude Fable 5.1 (medium), Claude Code or Claude Fable 5.1 (high), Claude Code?
They are level, at 200,000 tokens.