Which model leads ProteinGym Hard?

Q: Which model leads ProteinGym Hard?

Claude Mythos 5.1 tops the board at 49.3

ProteinGym Hard Leaderboard — 6 Models Ranked

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

The field · 6 measured

35.549.3

6 models measured, most on the official card harness. Claude Mythos 5.1 tops the board at 49.3.

6 measured·Lifecycle Updated Oct 17, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 6Bars show 35.5–49.3 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Mythos 5.1Anthropic49.3$10.0/M$50.0/M$0.609

02Claude Opus 5Anthropic47.7$5.0/M$25.0/M$0.314

03Claude Mythos 5Anthropic45.8$10.0/M$50.0/M$0.655

04Gemini 3.1 ProGoogle37$2.0/M$12.0/M$0.189

05Claude Sonnet 5Anthropic36.6$2.0/M$10.0/M$0.164

06GPT-5.6 SolOpenAI35.5$4.0/M$20.0/M$0.338

◆ 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 · 2 vendor cross-reference · 4 vendor-reported · 0 with source disagreement. How these tiers are assigned