List your company

Visual Question Answering on TickTockVQA (test)

56.41Hour Accuracy (Baseline)Llama-3.2-11B w/ Swap-DPO
9.693221.821633.9546.0784Mar 9, 2026

Evaluation results

MethodLinks
Llama-3.2-11B w/ Swap-DPOModel=Llama-3.2-11B, Training Stage=w/ Swap-DPO2026.0356.4164.4266.6973.6246.2248.481.030.974.854.6161.9358.79————
Llama-3.2-11B w/ TickTockVQAModel=Llama-3.2-11B, Training Stage=w/ TickTockVQA2026.0356.0564.466.6973.5745.7848.11.040.984.824.5662.5259.22————
Gemma3-12B w/ Swap-DPOModel=Gemma3-12B, Training Stage=w/ Swap-DPO2026.0346.6756.0157.5467.6435.3237.891.361.296.165.8581.8677.97————
Gemma3-12B w/ TickTockVQAModel=Gemma3-12B, Training Stage=w/ TickTockVQA2026.0346.3755.0454.3965.6834.2137.111.351.276.686.3481.6677.26————
Qwen2.5-VL-7B w/ Swap-DPOModel=Qwen2.5-VL-7B, Training Stage=w/ Swap-DPO2026.0335.3944.9846.1655.2923.0625.081.611.557.247.0196.4293.37————
Llama-3.2-11B w/ CtrlClockModel=Llama-3.2-11B, Training Stage=w/ CtrlClock2026.0333.2840.140.150.0923.04252.122.069.959.65128.1124.34————
Qwen2.5-VL-7B w/ TickTockVQAModel=Qwen2.5-VL-7B, Training Stage=w/ TickTockVQA2026.0333.1842.9441.5152.720.3422.761.731.668.538.19104.31100.2————
Llama-3.2-11B w/ SynClockModel=Llama-3.2-11B, Training Stage=w/ SynClock2026.0332.5540.6739.2447.0422.0923.82.12.049.779.54126.77123.79————
Qwen2.5-VL-7B w/ SynClockModel=Qwen2.5-VL-7B, Training Stage=w/ SynClock2026.0328.1137.5135.6847.1716.1218.282.152.099.69.35129.51126.34————
Qwen2.5-VL-7B w/ CtrlClockModel=Qwen2.5-VL-7B, Training Stage=w/ CtrlClock2026.0325.1633.8137.4546.8514.7517.082.182.119.589.28131.14127.2————
Qwen2.5-VL-7BModel=Qwen2.5-VL-7B, Training Stage=Baseline2026.0317.6525.2622.4432.146.047.262.472.4411.9611.81148.62146.76————
Gemma3-12BModel=Gemma3-12B, Training Stage=Baseline2026.031320.7510.6219.362.123.052.612.5914.4314.32156.49155.1————
Llama-3.2-11BModel=Llama-3.2-11B, Training Stage=Baseline2026.0311.4918.358.5816.851.412.022.592.5714.7914.7156.96155.67————
Gemma3-12BZero-shot=true2026.03————————————1310.622.12156.49
InternVL3-8BZero-shot=true2026.03————————————13.599.082.2159.92
It’s About TimeZero-shot=true2026.03————————————28.952518.54135.15
Llama-3.2-11BZero-shot=true2026.03————————————11.518.581.43156.96
Qwen2.5-VL-7BZero-shot=true2026.03————————————17.6522.446.04148.62
SpatialVLM-3BZero-shot=true2026.03————————————12.516.441.05161.68