Which model leads Toolathlon Pass@∞?

Q: Which model leads Toolathlon Pass@∞?

Claude Fable 5 tops the board at 55.6

Toolathlon Pass@∞ Leaderboard — 8 Models

Pro Mode — raw scores, one benchmark under the lensofficial card harness

The field · 8 measured

28.755.6

8 models measured, most on the official card harness. Claude Fable 5 tops the board at 55.6.

8 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 8Bars show 28.7–55.6 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Fable 5Anthropic55.6$10.0/M$50.0/M$0.540

02Claude Mythos 5Anthropic55.6$10.0/M$50.0/M$0.540

03Claude Opus 4.7Anthropic52.8$5.0/M$25.0/M$0.284

04Claude Opus 4.8Anthropic48.1$5.0/M$25.0/M$0.312

05Claude Opus 4.6Anthropic47.2$5.0/M$25.0/M$0.318

06Claude Sonnet 5Anthropic40.7$2.0/M$10.0/M$0.147

07Claude Sonnet 4.6Anthropic38$3.0/M$15.0/M$0.237

08Claude Sonnet 4.5Anthropic28.7$3.0/M$15.0/M$0.314

◆ solid = independently verified · aggregator attested · vendor attributed — outlined = cross-reference · source-attributed. Dimmed ◆ = confidence inferred. “+N alts” = alternate disclosures in the drawer with why-demoted. Prices per million tokens; $/point = input price ÷ score. Every row opens its model dossier.

Verification: 8 models scored · 0 independently verified · 8 vendor-reported · 0 with source disagreement. How these tiers are assigned