Category scores
Out of 100: 100 = the best tracked model in the category.
| Reasoning | 96 | |
| Mathematics | 91 | |
| Code | 90 | |
| Agents & real work | 75 | |
| Knowledge | 95 | |
| Long context | 96 | |
| Multimodal | — |
EditionUpdated daily
Ranking / Claude Fable 5.1
Claude Fable 5.1
Anthropic · Proprietary · context 1M. Ranked #4 of 26 with 866 ERAZ points out of 1000.
ERAZ rank#4/ 26
Points866/ 1000
Coverage86%
Benchmarks won0/ 14
Input price / M$10
Output price / M$50
Points over time
| Day | Points | Change |
|---|
Results on each benchmark
| Benchmark | Score | Rank | Out of 100 | Source |
|---|---|---|---|---|
| Humanity's Last Exam | 59.1% | #2 / 26 | 96 | src ↗ |
| ARC-AGI-2 | 90% | #7 / 13 | 95 | src ↗ |
| ARC-AGI-3 | not published | — | — | |
| FrontierMath (Tiers 1-3) | 90.2% | #4 / 16 | 96 | src ↗ |
| FrontierMath (Tier 4) | 87.8% | #4 / 16 | 88 | src ↗ |
| SWE-bench Pro | 81.2% | #3 / 9 | 90 | src ↗ |
| FrontierSWE v2 | 56.3% | #4 / 14 | 86 | src ↗ |
| Terminal-Bench 2.1 | 85% | #3 / 12 | 97 | src ↗ |
| OSWorld 2.0 | 41.7% | #9 / 11 | 57 | src ↗ |
| GDPval-AA | 1754 | #8 / 23 | 87 | src ↗ |
| GPQA Diamond | 93.7% | #5 / 15 | 96 | src ↗ |
| AA-Omniscience | 43.5 | #2 / 26 | 94 | src ↗ |
| AA-LCR | 85.3% | #4 / 26 | 96 | src ↗ |
| MMMU-Pro | not published | — | — |
Artificial Analysis Intelligence Index : 53.4 · Source page ↗
Nearby models in the ranking
</> Embed this ranking
Show Claude Fable 5.1's ranking on your site or in a README. The badge updates every day.
