Agentic benchmark
Toolathlon Verified Pass@3 leaderboard
Every model the catalog carries a published Toolathlon Verified Pass@3 value for, ranked by that value.
CategoryAgentic
MeasurePass@3
Tasks108 verified real-world tool-use tasks
DifficultyLong-horizon application tool use
Published byClaude Opus 5 System Card
Fraction of Toolathlon Verified tasks solved in at least one of three trials.
Toolathlon Verified Pass@3 ranking
2 models with a published Toolathlon Verified Pass@3 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Pass@3 |
|---|---|---|---|
| 1 |  Claude Opus 5 | Anthropic | 87.0 |
| 2 | Claude Fable 5.1 | Anthropic | 81.5 |
Evidence key: Observed
Rows are ordered by the value Claude Opus 5 System Card published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.