Which model leads OR-Bench (FRR)?

OR-Bench (FRR) Leaderboard — Model Scores

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

The field · 5 measured

2.58

5 models measured, most on the official card harness. Muse Spark tops the board at 8.

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 2.5–8 · ◆ solid = first-party or better · outlined = arm's-length

01Muse SparkMeta8———

02GPT-5.5OpenAI6.7$5.0/M$30.0/M$2.612

03Muse Spark 1.1Meta4.8$1.3/M$4.3/M$0.573

04Claude Opus 4.8Anthropic3.3$5.0/M$25.0/M$4.545

05Gemini 3.1 ProGoogle2.5$2.0/M$12.0/M$2.800

◆ 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