Which model leads M-LongDoc (multimodal long-document benchmark)?

M-LongDoc (multimodal long-document benchmark) Leaderboard — Model Scores

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

The field · 7 measured

13.941.4

7 models measured, most on the official card harness. GPT-4o tops the board at 41.4.

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 13.9–41.4 · ◆ solid = first-party or better · outlined = arm's-length

01GPT-4o+1 altOpenAI41.4$5.0/M$15.0/M$0.242

02MiniMax VL 01MiniMax32.5———

03Gemini 2.0 Flash ExpGoogle31.4———

04Claude 3.5 Sonnet+1 altAnthropic31.4$3.0/M$15.0/M$0.287

05Gemini 1.5 Pro+1 altGoogle26.2———

06InternVL2.5-78BOpenGVLab19.7———

07Llama 3.2 Instruct 90B (Vision)Meta13.9———

◆ 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 · 6 vendor cross-reference · 1 vendor-reported · 0 with source disagreement. How these tiers are assigned