Which model leads FullStackBench?

Q: Which model leads FullStackBench?

Claude Opus 4 tops the board at 70.3

FullStackBench Leaderboard — Model Scores

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

The field · 6 measured

62.970.3

6 models measured, most on the third-party eval harness. Claude Opus 4 tops the board at 70.3.

6 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 6Bars show 62.9–70.3 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Opus 4+1 altAnthropic70.3$15.0/M$75.0/M$0.640

02DeepSeek-R1+1 altDeepSeek70.1$2.0/M$4.0/M$0.043

03O3+1 altOpenAI69.3$2.0/M$8.0/M$0.072

04MiniMax M1 80K+1 altMiniMax68.3$0.55/M$2.2/M$0.020

05MiniMax M1 40K+1 altMiniMax67.6———

06Qwen3 235B A22B+1 altAlibaba62.9$0.70/M$2.8/M$0.028

◆ 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: 6 models scored · 0 independently verified · 4 vendor cross-reference · 2 vendor-reported · 0 with source disagreement. How these tiers are assigned