Vision Understanding on MMVP
86.33AccuracyGPT-5
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5Size=-2025.10 | 86.33 | |
| GPT4oModel Category=Proprietary Model2025.09 | 86.3 | |
| GPT-4oSize=-2025.10 | 84.67 | |
| Qwen2.5-VLSize=72B2025.10 | 82 | |
| Gemini 2.5 FlashSize=-2025.10 | 80.33 | |
| InternVL3.5Size=38B2025.10 | 80.33 | |
| ThinkMorphSize=7B, think mode=true2025.10 | 80.33 | |
| VisionZero-Qwen-7B (Real-World)Base Model=Qwen2.5-VL-7B, Variant=Real-World2025.09 | 79.5 | |
| VisionZero-Qwen-7B (CLEVR)Base Model=Qwen2.5-VL-7B, Variant=CLEVR2025.09 | 79.2 | |
| VisionZero-Qwen-7B (Chart)Base Model=Qwen2.5-VL-7B, Variant=Chart2025.09 | 77.9 | |
| Qwen2.5-VLSize=7B2025.10 | 77.33 | |
| Qwen2.5-VL-7B-InstructBase Model=Qwen2.5-VL-7B2025.09 | 76.8 | |
| InternVL3.5Size=8B2025.10 | 76.33 | |
| ViGaL-Snake+RotationBase Model=Qwen2.5-VL-7B2025.09 | 74.6 | |
| MM-Eureka-Qwen-7BBase Model=Qwen2.5-VL-7B2025.09 | 74.3 | |
| SPAR-3BLLM Params=2B, Model Category=Und. and Gen.2026.06 | 73.3 | |
| InternVL3-2BLLM Params=2B, Model Category=Und. Only2026.06 | 72.7 | |
| CoLVR2026.05 | 72 | |
| VLAA-Thinker-7BBase Model=Qwen2.5-VL-7B2025.09 | 71.6 | |
| OpenVLThinker-7BBase Model=Qwen2.5-VL-7B2025.09 | 71.3 | |
| BagelSize=7B, think mode=true2025.10 | 70.33 | |
| LVRSteps=82026.05 | 69.33 | |
| BAGEL-7BStage=Uni. 1 Stage2025.12 | 69.3 | |
| SPAR-1BLLM Params=1B, Model Category=Und. and Gen.2026.06 | 68.9 | |
| Mirage2026.05 | 68.33 | |
| UnisonStage=Uni. 2 Stage2025.12 | 67.3 | |
| InternVL3-1BLLM Params=1B, Model Category=Und. Only2026.06 | 67.3 | |
| Janus-proSize=7B2025.10 | 63.33 | |
| R1-OneVision-7BBase Model=Qwen2.5-VL-7B2025.09 | 61.3 | |
| BAGEL-1.5BStage=Uni. 1 Stage2025.12 | 54.7 | |
| BAGEL-7BLLM Params=3B, Model Category=Und. and Gen.2026.06 | 54.7 | |
| MetaMorph-8BLLM Params=8B, Model Category=Und. and Gen.2026.06 | 48.3 | |
| ChameleonSize=7B2025.10 | 47.67 | |
| Emu3-Chat-8BLLM Params=8B, Model Category=Und. Only2026.06 | 36.6 | |
| Dynamic-LLaVA-13B^ITFree=false, Image (prefill) Token=115, TFLOPs=4.72024.12 | 31.3 | |
| LLaVA-1.5-13BImage (prefill) Token=576, TFLOPs=19.62024.12 | 30.7 | |
| LLaVA-1.5-7BImage (prefill) Token=576, TFLOPs=10.12024.12 | 29.3 | |
| LLaVA-FastV (13B)Image (prefill) Token=144, TFLOPs=62024.12 | 28 | |
| Dynamic-LLaVA-7B^ITFree=false, Image (prefill) Token=115, TFLOPs=2.52024.12 | 26.3 | |
| LLaVA-FastV (7B)Free=true, Image (prefill) Token=144, TFLOPs=3.22024.12 | 24 | |
| VILA-U-7BLLM Params=7B, Model Category=Und. and Gen.2026.06 | 22 | |
| LLaVA-FastV† (7B)Free=false, Image (prefill) Token=144, TFLOPs=3.22024.12 | 16.7 | |
| LLaVA-1.5-7B+H2Ok-10, -0.5Image (prefill) Token=576, TFLOPs=10.12024.12 | 0 | |
| LLaVA-1.5-13b+H2Ok-10,-0.5Image (prefill) Token=576, TFLOPs=19.62024.12 | 0 | |
| Chameleon-7BLLM Params=7B, Model Category=Und. and Gen.2026.06 | 0 |