Which model leads BenchCAD w/ tools?

Q: Which model leads BenchCAD w/ tools?

Claude Opus 5.5 tops the board at 96.2

BenchCAD w/ tools Leaderboard — 5 Models

Pro Mode — raw scores, one benchmark under the lensthird-party eval harness

The field · 5 measured

81.696.2

5 models measured, most on the third-party eval harness. Claude Opus 5.5 tops the board at 96.2.

5 measured·5 new this week·Lifecycle Updated Nov 6, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 5Bars show 81.6–96.2 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Opus 5.5NEWAnthropic96.2$4.0/M$20.0/M$0.125

02GPT-6 AstraNEWOpenAI95.9$10.0/M$12.5/M$0.117

03Kimi K3.1 ProNEWMoonshot92.7$2.0/M$10.0/M$0.065

04Claude Fable 5.1NEWAnthropic92.6$10.0/M$50.0/M$0.324

05DeepSeek-V4.1-FlashNEWDeepSeek81.6$0.04/M$0.50/M$0.003

◆ 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: 5 models scored · 0 independently verified · 4 vendor cross-reference · 1 vendor-reported · 0 with source disagreement. How these tiers are assigned