Which model leads Legal Agent Benchmark, Full Public Set?

Q: Which model leads Legal Agent Benchmark, Full Public Set?

Claude Mythos 5 tops the board at 16.9

Legal Agent Benchmark, Full Public Set Leaderboard — Model Scores

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

The field · 5 measured

816.9

5 models measured, most on the official card harness. Claude Mythos 5 tops the board at 16.9.

5 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 5Bars show 8–16.9 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Mythos 5Anthropic16.9$10.0/M$50.0/M$1.775

02Claude Mythos PreviewAnthropic13.4———

03Claude Opus 4.8Anthropic9.6$5.0/M$25.0/M$1.562

04Claude Sonnet 5Anthropic8.9$2.0/M$10.0/M$0.674

05Claude Sonnet 4.6+1 altAnthropic8$3.0/M$15.0/M$1.125

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