Which model leads Blueprint-Bench 2?

Q: Which model leads Blueprint-Bench 2?

Claude Fable 5 tops the board at 38.6

Blueprint-Bench 2 Leaderboard — Model Scores

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

The field · 7 measured

038.6

7 models measured, most on the official card harness. Claude Fable 5 tops the board at 38.6.

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 0–38.6 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Fable 5+2 altsAnthropic38.6$10.0/M$50.0/M$0.777

02Gemini 3.5 Flash+3 altsGoogle33.6$1.5/M$9.0/M$0.156

03Gemini 3.1 Pro+1 altGoogle26.5$2.0/M$12.0/M$0.264

04Claude Opus 4.7+1 altAnthropic24.5$5.0/M$25.0/M$0.612

05Claude Opus 4.8Anthropic14.5$5.0/M$25.0/M$1.034

06Claude Sonnet 4.6Anthropic6.7$3.0/M$15.0/M$1.343

07Gemini 3 Flash PreviewGoogle0$0.50/M$3.0/M—

◆ 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 · 2 vendor cross-reference · 5 vendor-reported · 0 with source disagreement. How these tiers are assigned