Which model leads Toolathlon Avg turns?

Q: Which model leads Toolathlon Avg turns?

Claude Sonnet 4.5 tops the board at 32

Toolathlon Avg turns Leaderboard — 7 Models

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

The field · 7 measured

16.532

7 models measured, most on the official card harness. Claude Sonnet 4.5 tops the board at 32.

7 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 7Bars show 16.5–32 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Sonnet 4.5Anthropic32$3.0/M$15.0/M$0.281

02Claude Opus 4.7Anthropic25.9$5.0/M$25.0/M$0.579

03Claude Opus 4.8Anthropic24.5$5.0/M$25.0/M$0.612

04Claude Fable 5Anthropic19.8$10.0/M$50.0/M$1.515

05Claude Mythos 5Anthropic17.6$10.0/M$50.0/M$1.705

06Claude Opus 4.6Anthropic16.9$5.0/M$25.0/M$0.888

07Claude Sonnet 4.6Anthropic16.5$3.0/M$15.0/M$0.545

◆ 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: 7 models scored · 0 independently verified · 7 vendor-reported · 0 with source disagreement. How these tiers are assigned