Which model leads MMBench (EN)?

Q: Which model leads MMBench (EN)?

Gemini 2.5 Pro tops the board at 93.19

MMBench (EN) Leaderboard — 9 Models Ranked

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

The field · 9 measured

88.293.19

9 models measured, most on the official card harness. Gemini 2.5 Pro tops the board at 93.19.

9 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 9Bars show 88.2–93.19 · ◆ solid = first-party or better · outlined = arm's-length

01Gemini 2.5 Pro+1 altGoogle93.19$1.3/M$10.0/M$0.060

02GLM-4.6V (106B-A12B)+1 altZ.ai92.75———

03Qwen3 VL 235B A22B ReasoningAlibaba92.73P$0.40/M$4.0/M$0.024

04Step3 VL 10B+1 altStepFun92.38———

05Seed 1.5 VL+1 altByteDance92.11———

06GLM-4.6V-Flash (9B)+1 altZ.ai91.04$0.30/M$0.90/M$0.007

07Qwen3 VL Thinking (8B)+1 altAlibaba90.55$0.18/M$2.1/M$0.013

08MiMo VL RL 2508 (7B)+1 altXiaomi89.91———

09InternVL-3.5 (8B)+1 altOpenGVLab88.2———

◆ 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: 9 models scored · 0 independently verified · 8 vendor cross-reference · 1 vendor-reported · 0 with source disagreement. How these tiers are assigned