BENCHMARK EVIDENCE / ACTIVE
Humanity's Last Exam
multidisciplinary reasoning. Metric: accuracy. Direction: higher-is-better. Results below stay separated by evaluator evidence type and comparable group.
2observations
Anthropicevaluator
activestatus
2026-10-04verified
METHOD
Read the score with its configuration.
Scores from different comparable groups are intentionally not merged into one ranking. Reasoning effort, tools, fallback behavior, evaluator and benchmark version stay attached to every observation.
- Provider-reported launch result; tool setting is part of the observation identity.
vendor-reported
1 observationanthropic-fable-5-1-launch-table
| Model | Score | Reasoning | Tools | Source |
|---|---|---|---|---|
| Claude Fable 5.1 | 60.9% | not published | no tools | Evidence ↗ |
vendor-reported
1 observationanthropic-fable-5-1-launch-table-tools
| Model | Score | Reasoning | Tools | Source |
|---|---|---|---|---|
| Claude Fable 5.1 | 65.0% | not published | with tools | Evidence ↗ |