Toolathlon Verified Pass cubed (Toolathlon Verified Pass³)

We show this table for reference; we do not rank on it.

Data verified September 27, 202634 confirmed releases in the last 30 daysFollow model changes

Fraction of Toolathlon Verified tasks solved in all three independent trials.

Benchmark score on Toolathlon Verified Pass³ — September 27, 2026

We compile the Toolathlon Verified Pass³ rows from provider self-reports. Claude Opus 5 leads the table at 73.1%, followed by Claude Fable 5.1 (73.1%) and Claude Opus 5.5 (72.2%). We do not use these results to rank models overall.

1Proprietary

Claude Opus 5

Anthropic

73.1%

Overall 79.81

2Proprietary

Claude Fable 5.1

Anthropic

73.1%

Overall 83Context 1M

3Proprietary

Claude Opus 5.5

Anthropic

72.2%

Overall 86.98Context 1M

3 modelsAgenticCurrentDisplay onlyUpdated September 27, 2026

Benchmark score table (3 models)

Score

Claude Opus 5Anthropic · Closed

73.1%

Claude Fable 5.1Anthropic · Closed

73.1%

Claude Opus 5.5Anthropic · Closed

72.2%

Among the reported Toolathlon Verified Pass³ rows, Claude Opus 5 is first at 73.1%. The third row is 0.9 points behind. The broader top-10 range is 0.9 points, so many of the published results sit in a relatively narrow band.

3 models have been evaluated on Toolathlon Verified Pass³. The benchmark falls in the Agentic category. Toolathlon Verified Pass³ is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Toolathlon Verified Pass³

Year

2026

Tasks

108 verified real-world tool-use tasks

Format

All-three-trials pass rate

Difficulty

Long-horizon application tool use

Table 8.13.6.A reports this reliability metric separately from Pass@1 and Pass@3.

Claude Opus 5 System Card

Freshness and provenance

Version

Toolathlon Verified Pass³ 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does Toolathlon Verified Pass³ measure?

Fraction of Toolathlon Verified tasks solved in all three independent trials.

Which model scores highest on Toolathlon Verified Pass³?

Claude Opus 5 by Anthropic currently leads with a score of 73.1% on Toolathlon Verified Pass³.

How many models are evaluated on Toolathlon Verified Pass³?

3 AI models have been evaluated on Toolathlon Verified Pass³ on BenchLM.

Compare top models on Toolathlon Verified Pass³

Claude Opus 5 vs Claude Fable 5.1 Claude Fable 5.1 vs Claude Opus 5.5

Last updated: September 27, 2026 · BenchLM version Toolathlon Verified Pass³ 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.