benchgap
Calibration

Video-MME (w/o subtitle) → Video-MME (with subtitle)

Video-MME (with subtitle) is estimated from Video-MME (w/o subtitle) with a Michaelis–Menten curve fitted on 7 models measured on both: y = 2.0000·x / (1.13182 + x), R² = 0.80, cross-validated error 3.5 pp. It is used for 0 estimates.

Fitted on

ModelVideo-MME (w/o subtitle)Video-MME (with subtitle)
Claude Opus 4.581.4%77.6%
Gemini 3 Pro87.7%88.4%
GPT-5.285.8%86.0%
Kimi K2.583.2%87.4%
LFM3-VL-2B62.8%69.0%
Qwen3.5 397B83.7%87.5%
Qwen3.6-35B-A3B82.5%86.6%