OpenVLM Leaderboard
OpenCompass runs vision-language models through VLMEvalKit on a fixed set of image benchmarks, such as MMBench, MMStar and MathVista. The headline is the average score across that set.
The Hugging Face space dates from 2024-01-23 and has over 1,000 likes. Its per-benchmark columns are cataloged as separate boards, with 284 models in the JSON.
- Level
- University Undergraduates and entry-level professionals
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Short answer A number, word or short string matched to a key.
SenseNova-V6-5-Pro tops the leaderboard with 82.3
Best score per entry from the benchmark's own leaderboard, read on 2 Nov 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Gemini 2.5 Pro, at 80.1.
The newest model with a score here came out in Aug 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 82.3 SenseNova-V6-5-Pro
- 80.7 CongRong-v2.0
- 80.4 SenseNova-V6-Pro
- 80.1
Gemini 2.5 Pro
- 79.9 JT-VL-Chat-V3.0
- 79.9 GPT-5
- 79.1
InternVL3-78B
- 78.4 BlueLM-2.6-3B
- 78.0 GPT-5 mini
- 77.8
InternVL3-38B
- 77.7 Step-1o
- 77.4 SenseNova
- 77.0
InternVL2.5-78B-MPO
- 76.7 GLM-4v-Plus-20250111
- 76.5
Ovis2-34B
- 76.3 HunYuan-Standard-Vision
- 76.1
Qwen2.5-VL-72B
- 75.9 TeleMM
- 75.9 GPT-4.1
- 75.5 R-4B
- 75.4 ChatGPT-4o-latest
- 75.3
InternVL2.5-38B-MPO
- 75.3 GPT-4.5
- 75.2 BailingMM-Pro-0120
- 75.2
InternVL3-14B
- 74.8 Qwen2-VL-72B-Instruct
- 74.8
Qwen2.5-VL-32B
- 74.5 Qwen-VL-Max-0809
- 74.3 Kimi-VL-A3B-Thinking-2506
- 73.6
InternVL3-8B
- 73.6
SAIL-VL-1.6-8B
- 73.3
InternVL2.5-38B
- 73.3
Gemini 2.0 Pro
- 73.3
Ovis2-16B
- 73.0 Taiyi
- 72.6
Gemini 2.0 Flash
- 72.6 Ola-7b
- 72.6
InternVL3-9B
- 72.5 WeThink-Qwen2.5VL-7B
- 72.5 VARCO-VISION-2.0-14B
- 72.4 Step-1.5V
- 72.4 SAIL-VL-1.5-8B
- 72.2 GPT-5 nano
- 72.1 Gemini-1.5-Pro-002
- 72.1
InternVL2.5-26B-MPO
- 72.0 GPT-4o
- 71.8
Ovis2-8B
- 71.6 GPT-4o
- 71.5 BailingMM-Lite-1203
- 71.5 MUG-U-7B
- 71.4 GLM-4v-Plus
- 71.3
Ovis1.6-Gemma2-27B
- 71.0
InternVL2-Llama3-76B
- 71.0
InternVL2.5-26B
- 70.9 GPT-4o
- 70.9
Qwen2.5-VL-7B
- 70.8 BlueLM-2.5-3B
- 70.6 Claude 3.5 Sonnet (October 2024)
- 70.3
InternVL2.5-8B-MPO
- 70.2 MiniCPM-o-2_6
- 70.1 Claude 3.7 Sonnet
- 69.8
Ovis2-4B
- 69.7
InternVL2-40B
- 69.7 abab7-preview
- 69.3 valley2_dpo
- 69.3 Ovis-U1-3B
- 69.1 Kimi-VL-A3B-Instruct
- 68.9 Gemini-1.5-Flash-002
- 68.9 GPT-4.1 mini
- 68.8
Ovis1.6-Gemma2-9B
- 68.3
InternVL2_5-78B
- 68.1
InternVL2.5-8B
- 68.0 LLaVA-OneVision 72B
- 67.9 Claude 3.5 Sonnet
- 67.7 Ristretto-3B
- 67.6 LLaVA-OneVision-72B (SI)
- 67.6
NVLM-D-72B
- 67.5
Gemma 3 27B
- 67.4 POINTS1.5-Qwen2.5-7B
- 67.4 Valley-Eagle
- 67.2
InternVL2.5-4B-MPO
- 67.1 Qwen2-VL-7B-Instruct
- 67.1 valley2
- 67.0 bailingMM-mini
- 67.0 SAIL-VL-1.5-2B
- 66.9 Grok 2 Vision (1212)
- 66.8 VARCO-VISION-14B
- 66.4
InternVL2-26B
- 66.4
DeepSeek-VL2
- 66.1 BlueLM-V-3B
- 66.1 QTuneVL1.5-3B
- 65.9 Qwen-VL-Plus-0809
- 65.9 Kimi-VL-A3B-Thinking
- 65.6 MiMo-VL-7B
- 65.5 CongRong
- 65.2 MiniCPM-V-2_6
- 65.2
Ovis2-2B
- 65.1
InternVL2.5-4B
- 65.0 moonshot-v1-8k
- 64.9
InternVL2-8B-MPO
- 64.7
Phi-4-multimodal
- 64.6 QTuneVL1.5-2B
- 64.5
Gemini 1.5 Pro
- 64.5 RBDash-v1.5
- 64.5 Step-1.5V-mini
- 64.5
DeepSeek-VL2-Small
- 64.5
Qwen2.5-VL-3B
- 64.5
InternVL3-2B
- 64.1
InternVL2-8B
- 64.1 GPT-4o mini
- 64.0
Ovis1.5-Gemma2-9B
- 64.0
Molmo-72B
- 64.0 Aria
- 63.9 Yi-Vision
- 63.5 GPT-4V
- 63.5
Gemini 1.5 Flash
- 63.4
Llama 3.2 90B
- 63.3 VITA-1.5
- 62.8
Gemma 3 12B
- 62.6 MMAlaya2
- 62.5 POINTS-Qwen2.5-7B
- 62.0 OmChat-v2.0-13B
- 61.9 InternVL-Chat-V1-5
- 61.9
Ovis1.5-Llama3-8B
- 61.9 LLaVA-CoT
- 61.7 POINTS-Yi-1.5-9B
- 61.6 Flash-VL-2B-Dynamic-ISS
- 61.4
Ovis1.6-Llama3.2-3B
- 61.2
LLaVA-OneVision 7B (SI)
- 61.1
InternLM-XComposer2.5-7B
- 61.1 Long-VITA-16K
- 61.0
Pixtral 12B
- 61.0
SAIL-VL-2B
- 60.9
InternVL2.5-2B-MPO
- 60.8 GLM-4v
- 60.6
InternVL2-4B
- 60.2
LLaVA-OneVision 7B
- 59.9
InternVL2.5-2B
- 59.9 QTuneVL1-2B
- 59.6
Ovis2-1B
- 59.4 Aquila-VL-2B
- 59.2 GLM-4V-9B
- 59.2 VARCO-VISION-2.0-1.7B
- 58.8
InternLM-XComposer2-4KHD-7B
- 58.8
MiniCPM-Llama3-V 2.5
- 58.7 Granite Vision 3.3 2B
- 58.5
VILA1.5-40B
- 58.4 Qwen-VL-Max
- 58.3 WeMM
- 58.3
Cambrian-1-34B
- 58.1
DeepSeek-VL2-Tiny
- 57.9 Granite Vision 3.2 2B
- 57.7
Llama 3.2 11B
- 57.5 GPT-4.1 nano
- 57.4
Molmo-7B-D
- 57.3
Qwen2-VL-2B-Instruct
- 57.3 granite-vision-3.1-2b-preview
- 57.1 InternLM-XComposer2
- 57.0
InternVL3-1B
- 56.5 Reka Flash
- 56.3 CogVLM2-19B-Chat
- 56.3
Mini-InternVL-Chat-4B-V1-5
- 56.3
Idefics3-8B-Llama3
- 56.1
Gemini 1.0 Pro
- 55.9 XinYuan-VL-2B-Instruct
- 55.9 Ross-Qwen2-7B
- 55.8
Eagle-X5-34B-Chat
- 55.4
Gemma 3 4B
- 55.1
LLaVA-v1.6-34B
- 54.9
InternVL2.5-1B
- 54.8
InternVL2.5-1B-MPO
- 54.4 Claude 3 Opus
- 54.2 VITA
- 54.1
InternVL2-2B
- 54.1 H2OVL-2B
- 54.0 MiniMonkey
- 53.6
Phi-3-vision-128k-instruct
- 53.5 Claude 3 Sonnet
- 53.3
Cambrian-1-13B
- 53.0
Idefics2-8B
- 53.0 Phi-3.5-vision-instruct
- 52.9
Cambrian-1-8B
- 52.8 Llama-3-MixSense-v1.1
- 52.8 HawkVL-2B
- 52.3
Qwen-VL-Plus
- 52.2
SmolVLM2-2.2B-Instruct
- 52.0
Molmo-7B-O
- 52.0 Vintern-3B-beta
- 51.2 LLaVA-Next-Qwen-32B
- 51.1 XGen-MM-Instruct-Interleave-v1.5
- 50.9
Eagle-X5-13B
- 50.6 Claude 3 Haiku
- 50.2 XGen-MM-Instruct-DPO-v1.5
- 50.2
Janus-Pro-7B
- 49.8
Mini-InternVL-Chat-2B-V1-5
- 49.7 llama3-llava-next-8b
- 49.5
VILA1.5-13B
- 49.4 XVERSE-V-13B
- 49.4 Mantis-8B-Idefics2
- 48.7
Falcon2-11B-VLM
- 48.4 Monkey-Chat
- 48.4 Bunny-Llama-3-8B-V
- 48.4
LLaVA-NeXT-Interleave-7B-DPO
- 48.4
InternVL2-1B
- 48.2 360VL-70B
- 48.1
SmolVLM-Instruct
- 47.9 CogVLM-17B-Chat
- 47.9
MiniCPM-V 2.0
- 47.7 llava-v1.6-vicuna-13b
- 47.5
LLaVA-NeXT-Interleave-7B
- 47.5 Emu3-Chat
- 47.4
Eagle-X5-7B
- 47.0
InternLM-XComposer2-VL-1.8B
- 46.5
PaliGemma-3B-mix-448
- 46.2
OmniLMM-12B
- 46.2
DeepSeek-VL-7B-Chat
- 46.1
MolmoE-1B
- 45.9 llava-v1.6-mistral-7b
- 45.6 LLaVA-LLaMA-3-8B
- 45.2 Qwen-VL-Chat
- 44.8 llava-v1.6-vicuna-7b
- 44.8 SmolVLM-Instruct-DPO
- 44.3 Slime-8B
- 44.0
Llama-3-VILA1.5-8B
- 43.9 Monkey
- 43.8 LLaVA-InternLM2-20B (QLoRA)
- 43.5
Yi-VL-34B
- 43.5 H2OVL-800M
- 43.2 TransCore-M
- 43.1 LLaVA-InternLM2-7B (QLoRA)
- 43.0 Moondream2
- 42.9 Mantis-8B-siglip-llama3
- 42.5
ShareGPT4V-13B
- 42.5
LLaVA-OneVision 0.5B
- 42.5 Vintern-1B-v2
- 42.1
VILA1.5-3B
- 41.6 LLaVA-v1.5-13B (QLoRA)
- 41.5 Slime-13B
- 41.4 Parrot-7B
- 41.3
LLaVA-OneVision 0.5B (SI)
- 41.3
SmolVLM-500M-Instruct
- 41.1
Yi-VL-6B
- 41.0
MiniCPM-V
- 40.9 abab6.5s
- 40.9
SmolVLM2-500M-Video-Instruct
- 40.2
Janus-1.3B
- 39.9 Slime-7B
- 39.8
ShareGPT4V-7B
- 39.8 LLaVA-InternLM-7B (QLoRA)
- 39.8 ShareCaptioner
- 39.7
DeepSeek-VL-1.3B-Chat
- 39.4 AKI-4B
- 39.3
LLaVA-v1.5-13B
- 39.2 Emu2-Chat
- 38.6 SmolVLM-Synthetic
- 38.5 LLaVA-v1.5-7B (QLoRA)
- 38.5 Mantis-8B-clip-llama3
- 37.8
mPLUG-Owl2
- 36.9 llava-v1.5-7b
- 34.4
SmolVLM-256M-Instruct
- 34.2 Mantis-8B-Fuyu
- 33.2 Moondream1
- 33.1 MMAlaya
- 31.9 InternLM-XComposer
- 31.6
IDEFICS-80B-Instruct
- 31.3 LLaVA-v1-7B
- 31.1 instructblip-vicuna-7b
- 30.8
SmolVLM2-256M-Video-Instruct
- 28.3 Qwen-VL
- 27.2
IDEFICS-9B-Instruct
- 26.7 VisualGLM
- 26.5 PandaGPT-13B
- 26.5
Chameleon-30B
- 22.9 OpenFlamingo v2
- 21.9 MiniGPT-4-v1-7B
- 21.0
Kosmos-2
- 21.0
Chameleon-7B
- 18.4 MiniGPT-4-v2
- 1 SenseNova-V6-5-Pro 82.3
- 2 CongRong-v2.0 80.7
- 3 SenseNova-V6-Pro 80.4
- 4
Gemini 2.5 Pro Mar 2025 80.1
- 5 JT-VL-Chat-V3.0 79.9
- 6 GPT-5 79.9
- 7
InternVL3-78B 79.1
- 8 BlueLM-2.6-3B 78.4
- 9 GPT-5 mini 78.0
- 10
InternVL3-38B 77.8
- 11 Step-1o 77.7
- 12 SenseNova 77.4
- 13
InternVL2.5-78B-MPO 77.0
- 14 GLM-4v-Plus-20250111 76.7
- 15
Ovis2-34B 76.5
- 16 HunYuan-Standard-Vision 76.3
- 17
Qwen2.5-VL-72B 76.1
- 18 TeleMM 75.9
- 19 GPT-4.1 75.9
- 20 R-4B 75.5
- 21 ChatGPT-4o-latest 75.4
- 22
InternVL2.5-38B-MPO 75.3
- 23 GPT-4.5 75.3
- 24 BailingMM-Pro-0120 75.2
- 25
InternVL3-14B 75.2
- 26 Qwen2-VL-72B-Instruct 74.8
- 27
Qwen2.5-VL-32B 74.8
- 28 Qwen-VL-Max-0809 74.5
- 29 Kimi-VL-A3B-Thinking-2506 74.3
- 30
InternVL3-8B 73.6
- 31
SAIL-VL-1.6-8B 73.6
- 32
InternVL2.5-38B 73.3
- 33
Gemini 2.0 Pro 73.3
- 34
Ovis2-16B 73.3
- 35 Taiyi 73.0
- 36
Gemini 2.0 Flash Dec 2024 72.6
- 37 Ola-7b 72.6
- 38
InternVL3-9B 72.6
- 39 WeThink-Qwen2.5VL-7B 72.5
- 40 VARCO-VISION-2.0-14B 72.5
- 41 Step-1.5V 72.4
- 42 SAIL-VL-1.5-8B 72.4
- 43 GPT-5 nano 72.2
- 44 Gemini-1.5-Pro-002 72.1
- 45
InternVL2.5-26B-MPO 72.1
- 46 GPT-4o Nov 2024, detail-high 72.0
- 47
Ovis2-8B 71.8
- 48 GPT-4o Aug 2024, detail-high 71.6
- 49 BailingMM-Lite-1203 71.5
- 50 MUG-U-7B 71.5
- 51 GLM-4v-Plus 71.4
- 52
Ovis1.6-Gemma2-27B 71.3
- 53
InternVL2-Llama3-76B 71.0
- 54
InternVL2.5-26B 71.0
- 55 GPT-4o May 2024, detail-high 70.9
- 56
Qwen2.5-VL-7B 70.9
- 57 BlueLM-2.5-3B 70.8
- 58 Claude 3.5 Sonnet (October 2024) 70.6
- 59
InternVL2.5-8B-MPO 70.3
- 60 MiniCPM-o-2_6 70.2
- 61 Claude 3.7 Sonnet 70.1
- 62
Ovis2-4B 69.8
- 63
InternVL2-40B 69.7
- 64 abab7-preview 69.7
- 65 valley2_dpo 69.3
- 66 Ovis-U1-3B 69.3
- 67 Kimi-VL-A3B-Instruct 69.1
- 68 Gemini-1.5-Flash-002 68.9
- 69 GPT-4.1 mini 68.9
- 70
Ovis1.6-Gemma2-9B 68.8
- 71
InternVL2_5-78B 68.3
- 72
InternVL2.5-8B 68.1
- 73 LLaVA-OneVision 72B 68.0
- 74 Claude 3.5 Sonnet 67.9
- 75 Ristretto-3B 67.7
- 76 LLaVA-OneVision-72B (SI) 67.6
- 77
NVLM-D-72B 67.6
- 78
Gemma 3 27B 67.5
- 79 POINTS1.5-Qwen2.5-7B 67.4
- 80 Valley-Eagle 67.4
- 81
InternVL2.5-4B-MPO 67.2
- 82 Qwen2-VL-7B-Instruct 67.1
- 83 valley2 67.1
- 84 bailingMM-mini 67.0
- 85 SAIL-VL-1.5-2B 67.0
- 86 Grok 2 Vision (1212) 66.9
- 87 VARCO-VISION-14B 66.8
- 88
InternVL2-26B 66.4
- 89
DeepSeek-VL2 66.4
- 90 BlueLM-V-3B 66.1
- 91 QTuneVL1.5-3B 66.1
- 92 Qwen-VL-Plus-0809 65.9
- 93 Kimi-VL-A3B-Thinking 65.9
- 94 MiMo-VL-7B 65.6
- 95 CongRong 65.5
- 96 MiniCPM-V-2_6 65.2
- 97
Ovis2-2B 65.2
- 98
InternVL2.5-4B 65.1
- 99 moonshot-v1-8k 65.0
- 100
InternVL2-8B-MPO 64.9
- 101
Phi-4-multimodal 64.7
- 102 QTuneVL1.5-2B 64.6
- 103
Gemini 1.5 Pro May 2024 64.5
- 104 RBDash-v1.5 64.5
- 105 Step-1.5V-mini 64.5
- 106
DeepSeek-VL2-Small 64.5
- 107
Qwen2.5-VL-3B 64.5
- 108
InternVL3-2B 64.5
- 109
InternVL2-8B 64.1
- 110 GPT-4o mini detail-high 64.1
- 111
Ovis1.5-Gemma2-9B 64.0
- 112
Molmo-72B 64.0
- 113 Aria 64.0
- 114 Yi-Vision 63.9
- 115 GPT-4V detail-high 63.5
- 116
Gemini 1.5 Flash Sep 2024 63.5
- 117
Llama 3.2 90B 63.4
- 118 VITA-1.5 63.3
- 119
Gemma 3 12B 62.8
- 120 MMAlaya2 62.6
- 121 POINTS-Qwen2.5-7B 62.5
- 122 OmChat-v2.0-13B 62.0
- 123 InternVL-Chat-V1-5 61.9
- 124
Ovis1.5-Llama3-8B 61.9
- 125 LLaVA-CoT 61.9
- 126 POINTS-Yi-1.5-9B 61.7
- 127 Flash-VL-2B-Dynamic-ISS 61.6
- 128
Ovis1.6-Llama3.2-3B 61.4
- 129
LLaVA-OneVision 7B (SI) 61.2
- 130
InternLM-XComposer2.5-7B 61.1
- 131 Long-VITA-16K 61.1
- 132
Pixtral 12B 61.0
- 133
SAIL-VL-2B 61.0
- 134
InternVL2.5-2B-MPO 60.9
- 135 GLM-4v 60.8
- 136
InternVL2-4B 60.6
- 137
LLaVA-OneVision 7B 60.2
- 138
InternVL2.5-2B 59.9
- 139 QTuneVL1-2B 59.9
- 140
Ovis2-1B 59.6
- 141 Aquila-VL-2B 59.4
- 142 GLM-4V-9B 59.2
- 143 VARCO-VISION-2.0-1.7B 59.2
- 144
InternLM-XComposer2-4KHD-7B 58.8
- 145
MiniCPM-Llama3-V 2.5 58.8
- 146 Granite Vision 3.3 2B 58.7
- 147
VILA1.5-40B 58.5
- 148 Qwen-VL-Max 58.4
- 149 WeMM 58.3
- 150
Cambrian-1-34B 58.3
- 151
DeepSeek-VL2-Tiny 58.1
- 152 Granite Vision 3.2 2B 57.9
- 153
Llama 3.2 11B 57.7
- 154 GPT-4.1 nano 57.5
- 155
Molmo-7B-D 57.4
- 156
Qwen2-VL-2B-Instruct 57.3
- 157 granite-vision-3.1-2b-preview 57.3
- 158 InternLM-XComposer2 57.1
- 159
InternVL3-1B 57.0
- 160 Reka Flash 56.5
- 161 CogVLM2-19B-Chat 56.3
- 162
Mini-InternVL-Chat-4B-V1-5 56.3
- 163
Idefics3-8B-Llama3 56.3
- 164
Gemini 1.0 Pro 56.1
- 165 XinYuan-VL-2B-Instruct 55.9
- 166 Ross-Qwen2-7B 55.9
- 167
Eagle-X5-34B-Chat 55.8
- 168
Gemma 3 4B 55.4
- 169
LLaVA-v1.6-34B 55.1
- 170
InternVL2.5-1B 54.9
- 171
InternVL2.5-1B-MPO 54.8
- 172 Claude 3 Opus 54.4
- 173 VITA 54.2
- 174
InternVL2-2B 54.1
- 175 H2OVL-2B 54.1
- 176 MiniMonkey 54.0
- 177
Phi-3-vision-128k-instruct 53.6
- 178 Claude 3 Sonnet 53.5
- 179
Cambrian-1-13B 53.3
- 180
Idefics2-8B 53.0
- 181 Phi-3.5-vision-instruct 53.0
- 182
Cambrian-1-8B 52.9
- 183 Llama-3-MixSense-v1.1 52.8
- 184 HawkVL-2B 52.8
- 185
Qwen-VL-Plus 52.3
- 186
SmolVLM2-2.2B-Instruct 52.2
- 187
Molmo-7B-O 52.0
- 188 Vintern-3B-beta 52.0
- 189 LLaVA-Next-Qwen-32B 51.2
- 190 XGen-MM-Instruct-Interleave-v1.5 51.1
- 191
Eagle-X5-13B 50.9
- 192 Claude 3 Haiku 50.6
- 193 XGen-MM-Instruct-DPO-v1.5 50.2
- 194
Janus-Pro-7B 50.2
- 195
Mini-InternVL-Chat-2B-V1-5 49.8
- 196 llama3-llava-next-8b 49.7
- 197
VILA1.5-13B 49.5
- 198 XVERSE-V-13B 49.4
- 199 Mantis-8B-Idefics2 49.4
- 200
Falcon2-11B-VLM 48.7
- 201 Monkey-Chat 48.4
- 202 Bunny-Llama-3-8B-V 48.4
- 203
LLaVA-NeXT-Interleave-7B-DPO 48.4
- 204
InternVL2-1B 48.4
- 205 360VL-70B 48.2
- 206
SmolVLM-Instruct 48.1
- 207 CogVLM-17B-Chat 47.9
- 208
MiniCPM-V 2.0 47.9
- 209 llava-v1.6-vicuna-13b 47.7
- 210
LLaVA-NeXT-Interleave-7B 47.5
- 211 Emu3-Chat 47.5
- 212
Eagle-X5-7B 47.4
- 213
InternLM-XComposer2-VL-1.8B 47.0
- 214
PaliGemma-3B-mix-448 46.5
- 215
OmniLMM-12B 46.2
- 216
DeepSeek-VL-7B-Chat 46.2
- 217
MolmoE-1B 46.1
- 218 llava-v1.6-mistral-7b 45.9
- 219 LLaVA-LLaMA-3-8B 45.6
- 220 Qwen-VL-Chat 45.2
- 221 llava-v1.6-vicuna-7b 44.8
- 222 SmolVLM-Instruct-DPO 44.8
- 223 Slime-8B 44.3
- 224
Llama-3-VILA1.5-8B 44.0
- 225 Monkey 43.9
- 226 LLaVA-InternLM2-20B (QLoRA) 43.8
- 227
Yi-VL-34B 43.5
- 228 H2OVL-800M 43.5
- 229 TransCore-M 43.2
- 230 LLaVA-InternLM2-7B (QLoRA) 43.1
- 231 Moondream2 43.0
- 232 Mantis-8B-siglip-llama3 42.9
- 233
ShareGPT4V-13B 42.5
- 234
LLaVA-OneVision 0.5B 42.5
- 235 Vintern-1B-v2 42.5
- 236
VILA1.5-3B 42.1
- 237 LLaVA-v1.5-13B (QLoRA) 41.6
- 238 Slime-13B 41.5
- 239 Parrot-7B 41.4
- 240
LLaVA-OneVision 0.5B (SI) 41.3
- 241
SmolVLM-500M-Instruct 41.3
- 242
Yi-VL-6B 41.1
- 243
MiniCPM-V 41.0
- 244 abab6.5s 40.9
- 245
SmolVLM2-500M-Video-Instruct 40.9
- 246
Janus-1.3B 40.2
- 247 Slime-7B 39.9
- 248
ShareGPT4V-7B 39.8
- 249 LLaVA-InternLM-7B (QLoRA) 39.8
- 250 ShareCaptioner 39.8
- 251
DeepSeek-VL-1.3B-Chat 39.7
- 252 AKI-4B 39.4
- 253
LLaVA-v1.5-13B 39.3
- 254 Emu2-Chat 39.2
- 255 SmolVLM-Synthetic 38.6
- 256 LLaVA-v1.5-7B (QLoRA) 38.5
- 257 Mantis-8B-clip-llama3 38.5
- 258
mPLUG-Owl2 37.8
- 259 llava-v1.5-7b 36.9
- 260
SmolVLM-256M-Instruct 34.4
- 261 Mantis-8B-Fuyu 34.2
- 262 Moondream1 33.2
- 263 MMAlaya 33.1
- 264 InternLM-XComposer 31.9
- 265
IDEFICS-80B-Instruct 31.6
- 266 LLaVA-v1-7B 31.3
- 267 instructblip-vicuna-7b 31.1
- 268
SmolVLM2-256M-Video-Instruct 30.8
- 269 Qwen-VL 28.3
- 270
IDEFICS-9B-Instruct 27.2
- 271 VisualGLM 26.7
- 272 PandaGPT-13B 26.5
- 273
Chameleon-30B 26.5
- 274 OpenFlamingo v2 22.9
- 275 MiniGPT-4-v1-7B 21.9
- 276
Kosmos-2 21.0
- 277
Chameleon-7B 21.0
- 278 MiniGPT-4-v2 18.4
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | SenseNova-V6-5-Pro | 82.3 | Sep 2025 | Official leaderboard | |
| 2 | CongRong-v2.0 | 80.7 | May 2025 | Official leaderboard | |
| 3 | SenseNova-V6-Pro | 80.4 | May 2025 | Official leaderboard | |
| 4 | | 80.1 | Mar 2025 | Official leaderboard | |
| 5 | JT-VL-Chat-V3.0 | 79.9 | Aug 2025 | Official leaderboard | |
| 6 | GPT-5 | 79.9 | Aug 2025 | Official leaderboard | |
| 7 | | 79.1 | Apr 2025 | Official leaderboard | |
| 8 | BlueLM-2.6-3B | 78.4 | Sep 2025 | Official leaderboard | |
| 9 | GPT-5 mini | 78.0 | Aug 2025 | Official leaderboard | |
| 10 | | 77.8 | Apr 2025 | Official leaderboard | |
| 11 | Step-1o | 77.7 | Jan 2025 | Official leaderboard | |
| 12 | SenseNova | 77.4 | Dec 2024 | Official leaderboard | |
| 13 | | 77.0 | Dec 2024 | Official leaderboard | |
| 14 | GLM-4v-Plus-20250111 | 76.7 | Jan 2025 | Official leaderboard | |
| 15 | | 76.5 | Feb 2025 | Official leaderboard | |
| 16 | HunYuan-Standard-Vision | 76.3 | Jan 2025 | Official leaderboard | |
| 17 | | 76.1 | Jan 2025 | Official leaderboard | |
| 18 | TeleMM | 75.9 | Dec 2024 | Official leaderboard | |
| 19 | GPT-4.1 | 75.9 | Apr 2025 | Official leaderboard | |
| 20 | R-4B | 75.5 | Aug 2025 | Official leaderboard | |
| 21 | ChatGPT-4o-latest | 75.4 | Apr 2025 | Official leaderboard | |
| 22 | | 75.3 | Dec 2024 | Official leaderboard | |
| 23 | GPT-4.5 | 75.3 | Feb 2025 | Official leaderboard | |
| 24 | BailingMM-Pro-0120 | 75.2 | Jan 2025 | Official leaderboard | |
| 25 | | 75.2 | Apr 2025 | Official leaderboard | |
| 26 | Qwen2-VL-72B-Instruct | 74.8 | Aug 2024 | Official leaderboard | |
| 27 | | 74.8 | Mar 2025 | Official leaderboard | |
| 28 | Qwen-VL-Max-0809 | 74.5 | Sep 2024 | Official leaderboard | |
| 29 | Kimi-VL-A3B-Thinking-2506 | 74.3 | Jun 2025 | Official leaderboard | |
| 30 | | 73.6 | Apr 2025 | Official leaderboard | |
| 31 | | 73.6 | Apr 2025 | Official leaderboard | |
| 32 | | 73.3 | Dec 2024 | Official leaderboard | |
| 33 | | 73.3 | Feb 2025 | Official leaderboard | |
| 34 | | 73.3 | Feb 2025 | Official leaderboard | |
| 35 | Taiyi | 73.0 | Dec 2024 | Official leaderboard | |
| 36 | | 72.6 | Dec 2024 | Official leaderboard | |
| 37 | Ola-7b | 72.6 | Feb 2025 | Official leaderboard | |
| 38 | | 72.6 | Apr 2025 | Official leaderboard | |
| 39 | WeThink-Qwen2.5VL-7B | 72.5 | May 2025 | Official leaderboard | |
| 40 | VARCO-VISION-2.0-14B | 72.5 | Aug 2025 | Official leaderboard | |
| 41 | Step-1.5V | 72.4 | Oct 2024 | Official leaderboard | |
| 42 | SAIL-VL-1.5-8B | 72.4 | Apr 2025 | Official leaderboard | |
| 43 | GPT-5 nano | 72.2 | Aug 2025 | Official leaderboard | |
| 44 | Gemini-1.5-Pro-002 | 72.1 | Dec 2024 | Official leaderboard | |
| 45 | | 72.1 | Dec 2024 | Official leaderboard | |
| 46 | GPT-4o Nov 2024 | 72.0 | detail-high | Nov 2024 | Official leaderboard |
| 47 | | 71.8 | Feb 2025 | Official leaderboard | |
| 48 | GPT-4o Aug 2024 | 71.6 | detail-high | Aug 2024 | Official leaderboard |
| 49 | BailingMM-Lite-1203 | 71.5 | Dec 2024 | Official leaderboard | |
| 50 | MUG-U-7B | 71.5 | Mar 2025 | Official leaderboard | |
| 51 | GLM-4v-Plus | 71.4 | Dec 2024 | Official leaderboard | |
| 52 | | 71.3 | Nov 2024 | Official leaderboard | |
| 53 | | 71.0 | Jul 2024 | Official leaderboard | |
| 54 | | 71.0 | Dec 2024 | Official leaderboard | |
| 55 | GPT-4o May 2024 | 70.9 | detail-high | May 2024 | Official leaderboard |
| 56 | | 70.9 | Jan 2025 | Official leaderboard | |
| 57 | BlueLM-2.5-3B | 70.8 | Jul 2025 | Official leaderboard | |
| 58 | Claude 3.5 Sonnet (October 2024) | 70.6 | Oct 2024 | Official leaderboard | |
| 59 | | 70.3 | Dec 2024 | Official leaderboard | |
| 60 | MiniCPM-o-2_6 | 70.2 | Jan 2025 | Official leaderboard | |
| 61 | Claude 3.7 Sonnet | 70.1 | Feb 2025 | Official leaderboard | |
| 62 | | 69.8 | Feb 2025 | Official leaderboard | |
| 63 | | 69.7 | Jul 2024 | Official leaderboard | |
| 64 | abab7-preview | 69.7 | Dec 2024 | Official leaderboard | |
| 65 | valley2_dpo | 69.3 | May 2025 | Official leaderboard | |
| 66 | Ovis-U1-3B | 69.3 | Jul 2025 | Official leaderboard | |
| 67 | Kimi-VL-A3B-Instruct | 69.1 | Apr 2025 | Official leaderboard | |
| 68 | Gemini-1.5-Flash-002 | 68.9 | Dec 2024 | Official leaderboard | |
| 69 | GPT-4.1 mini | 68.9 | Apr 2025 | Official leaderboard | |
| 70 | | 68.8 | Sep 2024 | Official leaderboard | |
| 71 | | 68.3 | Dec 2024 | Official leaderboard | |
| 72 | | 68.1 | Dec 2024 | Official leaderboard | |
| 73 | LLaVA-OneVision 72B | 68.0 | Aug 2024 | Official leaderboard | |
| 74 | Claude 3.5 Sonnet | 67.9 | Jun 2024 | Official leaderboard | |
| 75 | Ristretto-3B | 67.7 | Apr 2025 | Official leaderboard | |
| 76 | LLaVA-OneVision-72B (SI) | 67.6 | Sep 2024 | Official leaderboard | |
| 77 | | 67.6 | Sep 2024 | Official leaderboard | |
| 78 | | 67.5 | Mar 2025 | Official leaderboard | |
| 79 | POINTS1.5-Qwen2.5-7B | 67.4 | Dec 2024 | Official leaderboard | |
| 80 | Valley-Eagle | 67.4 | Dec 2024 | Official leaderboard | |
| 81 | | 67.2 | Dec 2024 | Official leaderboard | |
| 82 | Qwen2-VL-7B-Instruct | 67.1 | Aug 2024 | Official leaderboard | |
| 83 | valley2 | 67.1 | May 2025 | Official leaderboard | |
| 84 | bailingMM-mini | 67.0 | Oct 2024 | Official leaderboard | |
| 85 | SAIL-VL-1.5-2B | 67.0 | Apr 2025 | Official leaderboard | |
| 86 | Grok 2 Vision (1212) | 66.9 | Dec 2024 | Official leaderboard | |
| 87 | VARCO-VISION-14B | 66.8 | Jan 2025 | Official leaderboard | |
| 88 | | 66.4 | Jul 2024 | Official leaderboard | |
| 89 | | 66.4 | Dec 2024 | Official leaderboard | |
| 90 | BlueLM-V-3B | 66.1 | Oct 2024 | Official leaderboard | |
| 91 | QTuneVL1.5-3B | 66.1 | Aug 2025 | Official leaderboard | |
| 92 | Qwen-VL-Plus-0809 | 65.9 | Sep 2024 | Official leaderboard | |
| 93 | Kimi-VL-A3B-Thinking | 65.9 | Apr 2025 | Official leaderboard | |
| 94 | MiMo-VL-7B | 65.6 | Jul 2025 | Official leaderboard | |
| 95 | CongRong | 65.5 | Jun 2024 | Official leaderboard | |
| 96 | MiniCPM-V-2_6 | 65.2 | Aug 2024 | Official leaderboard | |
| 97 | | 65.2 | Feb 2025 | Official leaderboard | |
| 98 | | 65.1 | Dec 2024 | Official leaderboard | |
| 99 | moonshot-v1-8k | 65.0 | Mar 2025 | Official leaderboard | |
| 100 | | 64.9 | Nov 2024 | Official leaderboard | |
| 101 | | 64.7 | Feb 2025 | Official leaderboard | |
| 102 | QTuneVL1.5-2B | 64.6 | Aug 2025 | Official leaderboard | |
| 103 | | 64.5 | May 2024 | Official leaderboard | |
| 104 | RBDash-v1.5 | 64.5 | Nov 2024 | Official leaderboard | |
| 105 | Step-1.5V-mini | 64.5 | Dec 2024 | Official leaderboard | |
| 106 | | 64.5 | Dec 2024 | Official leaderboard | |
| 107 | | 64.5 | Jan 2025 | Official leaderboard | |
| 108 | | 64.5 | Apr 2025 | Official leaderboard | |
| 109 | | 64.1 | Jul 2024 | Official leaderboard | |
| 110 | GPT-4o mini | 64.1 | detail-high | Jul 2024 | Official leaderboard |
| 111 | | 64.0 | Jul 2024 | Official leaderboard | |
| 112 | | 64.0 | Sep 2024 | Official leaderboard | |
| 113 | Aria | 64.0 | Sep 2024 | Official leaderboard | |
| 114 | Yi-Vision | 63.9 | Aug 2024 | Official leaderboard | |
| 115 | GPT-4V | 63.5 | detail-high | Nov 2023 | Official leaderboard |
| 116 | | 63.5 | Aug 2024 | Official leaderboard | |
| 117 | | 63.4 | Sep 2024 | Official leaderboard | |
| 118 | VITA-1.5 | 63.3 | Dec 2024 | Official leaderboard | |
| 119 | | 62.8 | Mar 2025 | Official leaderboard | |
| 120 | MMAlaya2 | 62.6 | Aug 2024 | Official leaderboard | |
| 121 | POINTS-Qwen2.5-7B | 62.5 | Oct 2024 | Official leaderboard | |
| 122 | OmChat-v2.0-13B | 62.0 | Aug 2024 | Official leaderboard | |
| 123 | InternVL-Chat-V1-5 | 61.9 | Apr 2024 | Official leaderboard | |
| 124 | | 61.9 | Jul 2024 | Official leaderboard | |
| 125 | LLaVA-CoT | 61.9 | Jan 2025 | Official leaderboard | |
| 126 | POINTS-Yi-1.5-9B | 61.7 | Oct 2024 | Official leaderboard | |
| 127 | Flash-VL-2B-Dynamic-ISS | 61.6 | May 2025 | Official leaderboard | |
| 128 | | 61.4 | Oct 2024 | Official leaderboard | |
| 129 | | 61.2 | Aug 2024 | Official leaderboard | |
| 130 | | 61.1 | Jul 2024 | Official leaderboard | |
| 131 | Long-VITA-16K | 61.1 | Jun 2025 | Official leaderboard | |
| 132 | | 61.0 | Sep 2024 | Official leaderboard | |
| 133 | | 61.0 | Dec 2024 | Official leaderboard | |
| 134 | | 60.9 | Dec 2024 | Official leaderboard | |
| 135 | GLM-4v | 60.8 | May 2024 | Official leaderboard | |
| 136 | | 60.6 | Jul 2024 | Official leaderboard | |
| 137 | | 60.2 | Aug 2024 | Official leaderboard | |
| 138 | | 59.9 | Dec 2024 | Official leaderboard | |
| 139 | QTuneVL1-2B | 59.9 | May 2025 | Official leaderboard | |
| 140 | | 59.6 | Feb 2025 | Official leaderboard | |
| 141 | Aquila-VL-2B | 59.4 | Oct 2024 | Official leaderboard | |
| 142 | GLM-4V-9B | 59.2 | Jun 2024 | Official leaderboard | |
| 143 | VARCO-VISION-2.0-1.7B | 59.2 | Aug 2025 | Official leaderboard | |
| 144 | | 58.8 | Apr 2024 | Official leaderboard | |
| 145 | | 58.8 | May 2024 | Official leaderboard | |
| 146 | Granite Vision 3.3 2B | 58.7 | Jun 2025 | Official leaderboard | |
| 147 | | 58.5 | Apr 2024 | Official leaderboard | |
| 148 | Qwen-VL-Max | 58.4 | Jan 2024 | Official leaderboard | |
| 149 | WeMM | 58.3 | Jun 2024 | Official leaderboard | |
| 150 | | 58.3 | Jun 2024 | Official leaderboard | |
| 151 | | 58.1 | Dec 2024 | Official leaderboard | |
| 152 | Granite Vision 3.2 2B | 57.9 | Feb 2025 | Official leaderboard | |
| 153 | | 57.7 | Sep 2024 | Official leaderboard | |
| 154 | GPT-4.1 nano | 57.5 | Apr 2025 | Official leaderboard | |
| 155 | | 57.4 | Sep 2024 | Official leaderboard | |
| 156 | | 57.3 | Aug 2024 | Official leaderboard | |
| 157 | granite-vision-3.1-2b-preview | 57.3 | Jun 2025 | Official leaderboard | |
| 158 | InternLM-XComposer2 | 57.1 | Jan 2024 | Official leaderboard | |
| 159 | | 57.0 | Apr 2025 | Official leaderboard | |
| 160 | Reka Flash | 56.5 | Feb 2024 | Official leaderboard | |
| 161 | CogVLM2-19B-Chat | 56.3 | May 2024 | Official leaderboard | |
| 162 | | 56.3 | May 2024 | Official leaderboard | |
| 163 | | 56.3 | Aug 2024 | Official leaderboard | |
| 164 | | 56.1 | Dec 2023 | Official leaderboard | |
| 165 | XinYuan-VL-2B-Instruct | 55.9 | Sep 2024 | Official leaderboard | |
| 166 | Ross-Qwen2-7B | 55.9 | Jan 2025 | Official leaderboard | |
| 167 | | 55.8 | Sep 2024 | Official leaderboard | |
| 168 | | 55.4 | Mar 2025 | Official leaderboard | |
| 169 | | 55.1 | Jan 2024 | Official leaderboard | |
| 170 | | 54.9 | Dec 2024 | Official leaderboard | |
| 171 | | 54.8 | Dec 2024 | Official leaderboard | |
| 172 | Claude 3 Opus | 54.4 | Feb 2024 | Official leaderboard | |
| 173 | VITA | 54.2 | Aug 2024 | Official leaderboard | |
| 174 | | 54.1 | Jul 2024 | Official leaderboard | |
| 175 | H2OVL-2B | 54.1 | Oct 2024 | Official leaderboard | |
| 176 | MiniMonkey | 54.0 | Sep 2024 | Official leaderboard | |
| 177 | | 53.6 | May 2024 | Official leaderboard | |
| 178 | Claude 3 Sonnet | 53.5 | Feb 2024 | Official leaderboard | |
| 179 | | 53.3 | Jun 2024 | Official leaderboard | |
| 180 | | 53.0 | Apr 2024 | Official leaderboard | |
| 181 | Phi-3.5-vision-instruct | 53.0 | Aug 2024 | Official leaderboard | |
| 182 | | 52.9 | Jun 2024 | Official leaderboard | |
| 183 | Llama-3-MixSense-v1.1 | 52.8 | Aug 2024 | Official leaderboard | |
| 184 | HawkVL-2B | 52.8 | Jun 2025 | Official leaderboard | |
| 185 | | 52.3 | Jan 2024 | Official leaderboard | |
| 186 | | 52.2 | Feb 2025 | Official leaderboard | |
| 187 | | 52.0 | Sep 2024 | Official leaderboard | |
| 188 | Vintern-3B-beta | 52.0 | Oct 2024 | Official leaderboard | |
| 189 | LLaVA-Next-Qwen-32B | 51.2 | Aug 2024 | Official leaderboard | |
| 190 | XGen-MM-Instruct-Interleave-v1.5 | 51.1 | Sep 2024 | Official leaderboard | |
| 191 | | 50.9 | Aug 2024 | Official leaderboard | |
| 192 | Claude 3 Haiku | 50.6 | Mar 2024 | Official leaderboard | |
| 193 | XGen-MM-Instruct-DPO-v1.5 | 50.2 | Sep 2024 | Official leaderboard | |
| 194 | | 50.2 | Jan 2025 | Official leaderboard | |
| 195 | | 49.8 | May 2024 | Official leaderboard | |
| 196 | llama3-llava-next-8b | 49.7 | Apr 2024 | Official leaderboard | |
| 197 | | 49.5 | Apr 2024 | Official leaderboard | |
| 198 | XVERSE-V-13B | 49.4 | May 2024 | Official leaderboard | |
| 199 | Mantis-8B-Idefics2 | 49.4 | Aug 2024 | Official leaderboard | |
| 200 | | 48.7 | May 2024 | Official leaderboard | |
| 201 | Monkey-Chat | 48.4 | Jan 2024 | Official leaderboard | |
| 202 | Bunny-Llama-3-8B-V | 48.4 | Apr 2024 | Official leaderboard | |
| 203 | | 48.4 | Jun 2024 | Official leaderboard | |
| 204 | | 48.4 | Jul 2024 | Official leaderboard | |
| 205 | 360VL-70B | 48.2 | May 2024 | Official leaderboard | |
| 206 | | 48.1 | Nov 2024 | Official leaderboard | |
| 207 | CogVLM-17B-Chat | 47.9 | Nov 2023 | Official leaderboard | |
| 208 | | 47.9 | Apr 2024 | Official leaderboard | |
| 209 | llava-v1.6-vicuna-13b | 47.7 | Jan 2024 | Official leaderboard | |
| 210 | | 47.5 | Jun 2024 | Official leaderboard | |
| 211 | Emu3-Chat | 47.5 | Sep 2024 | Official leaderboard | |
| 212 | | 47.4 | Aug 2024 | Official leaderboard | |
| 213 | | 47.0 | Apr 2024 | Official leaderboard | |
| 214 | | 46.5 | May 2024 | Official leaderboard | |
| 215 | | 46.2 | Jan 2024 | Official leaderboard | |
| 216 | | 46.2 | Mar 2024 | Official leaderboard | |
| 217 | | 46.1 | Sep 2024 | Official leaderboard | |
| 218 | llava-v1.6-mistral-7b | 45.9 | Jan 2024 | Official leaderboard | |
| 219 | LLaVA-LLaMA-3-8B | 45.6 | May 2024 | Official leaderboard | |
| 220 | Qwen-VL-Chat | 45.2 | Aug 2023 | Official leaderboard | |
| 221 | llava-v1.6-vicuna-7b | 44.8 | Jan 2024 | Official leaderboard | |
| 222 | SmolVLM-Instruct-DPO | 44.8 | Jan 2025 | Official leaderboard | |
| 223 | Slime-8B | 44.3 | Sep 2024 | Official leaderboard | |
| 224 | | 44.0 | Apr 2024 | Official leaderboard | |
| 225 | Monkey | 43.9 | Nov 2023 | Official leaderboard | |
| 226 | LLaVA-InternLM2-20B (QLoRA) | 43.8 | Jan 2024 | Official leaderboard | |
| 227 | | 43.5 | Dec 2023 | Official leaderboard | |
| 228 | H2OVL-800M | 43.5 | Oct 2024 | Official leaderboard | |
| 229 | TransCore-M | 43.2 | Apr 2024 | Official leaderboard | |
| 230 | LLaVA-InternLM2-7B (QLoRA) | 43.1 | Jan 2024 | Official leaderboard | |
| 231 | Moondream2 | 43.0 | Oct 2024 | Official leaderboard | |
| 232 | Mantis-8B-siglip-llama3 | 42.9 | Aug 2024 | Official leaderboard | |
| 233 | | 42.5 | Dec 2023 | Official leaderboard | |
| 234 | | 42.5 | Aug 2024 | Official leaderboard | |
| 235 | Vintern-1B-v2 | 42.5 | Nov 2024 | Official leaderboard | |
| 236 | | 42.1 | Apr 2024 | Official leaderboard | |
| 237 | LLaVA-v1.5-13B (QLoRA) | 41.6 | Dec 2023 | Official leaderboard | |
| 238 | Slime-13B | 41.5 | Sep 2024 | Official leaderboard | |
| 239 | Parrot-7B | 41.4 | Aug 2024 | Official leaderboard | |
| 240 | | 41.3 | Aug 2024 | Official leaderboard | |
| 241 | | 41.3 | Jan 2025 | Official leaderboard | |
| 242 | | 41.1 | Dec 2023 | Official leaderboard | |
| 243 | | 41.0 | Jan 2024 | Official leaderboard | |
| 244 | abab6.5s | 40.9 | Dec 2024 | Official leaderboard | |
| 245 | | 40.9 | Feb 2025 | Official leaderboard | |
| 246 | | 40.2 | Oct 2024 | Official leaderboard | |
| 247 | Slime-7B | 39.9 | Sep 2024 | Official leaderboard | |
| 248 | | 39.8 | Nov 2023 | Official leaderboard | |
| 249 | LLaVA-InternLM-7B (QLoRA) | 39.8 | Dec 2023 | Official leaderboard | |
| 250 | ShareCaptioner | 39.8 | Jan 2024 | Official leaderboard | |
| 251 | | 39.7 | Mar 2024 | Official leaderboard | |
| 252 | AKI-4B | 39.4 | Mar 2025 | Official leaderboard | |
| 253 | | 39.3 | Oct 2023 | Official leaderboard | |
| 254 | Emu2-Chat | 39.2 | Dec 2023 | Official leaderboard | |
| 255 | SmolVLM-Synthetic | 38.6 | Jan 2025 | Official leaderboard | |
| 256 | LLaVA-v1.5-7B (QLoRA) | 38.5 | Dec 2023 | Official leaderboard | |
| 257 | Mantis-8B-clip-llama3 | 38.5 | Aug 2024 | Official leaderboard | |
| 258 | | 37.8 | Nov 2023 | Official leaderboard | |
| 259 | llava-v1.5-7b | 36.9 | Oct 2023 | Official leaderboard | |
| 260 | | 34.4 | Jan 2025 | Official leaderboard | |
| 261 | Mantis-8B-Fuyu | 34.2 | Sep 2024 | Official leaderboard | |
| 262 | Moondream1 | 33.2 | Sep 2024 | Official leaderboard | |
| 263 | MMAlaya | 33.1 | Jan 2024 | Official leaderboard | |
| 264 | InternLM-XComposer | 31.9 | Sep 2023 | Official leaderboard | |
| 265 | | 31.6 | Jul 2023 | Official leaderboard | |
| 266 | LLaVA-v1-7B | 31.3 | Apr 2023 | Official leaderboard | |
| 267 | instructblip-vicuna-7b | 31.1 | May 2023 | Official leaderboard | |
| 268 | | 30.8 | Feb 2025 | Official leaderboard | |
| 269 | Qwen-VL | 28.3 | Aug 2023 | Official leaderboard | |
| 270 | | 27.2 | Jul 2023 | Official leaderboard | |
| 271 | VisualGLM | 26.7 | May 2023 | Official leaderboard | |
| 272 | PandaGPT-13B | 26.5 | May 2023 | Official leaderboard | |
| 273 | | 26.5 | Jun 2024 | Official leaderboard | |
| 274 | OpenFlamingo v2 | 22.9 | Jun 2023 | Official leaderboard | |
| 275 | MiniGPT-4-v1-7B | 21.9 | Apr 2023 | Official leaderboard | |
| 276 | | 21.0 | Jun 2023 | Official leaderboard | |
| 277 | | 21.0 | Jun 2024 | Official leaderboard | |
| 278 | MiniGPT-4-v2 | 18.4 | Oct 2023 | Official leaderboard |
7 models have held number one since its release in Jan 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No lab model card reports it yet
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.
More in Other
- Personal Superintelligence Index (Meta) In use Meta's composite of seven personal and knowledge-work evals: Agents' Last Exam, AutomationBench-AA, FocusBench, JobBench, GDP.pdf, VBT and DRACO.
- Artificial Analysis Intelligence Index v5 In use Version 5 of Artificial Analysis's index: nine evaluations in four equal categories, most with private test sets, run three times each in its own agent harness.
Gemini 4 Carbon 59.0
- Anthropic ECI (AECI) Only in system cards Index that combines a basket of capability benchmarks into one capability score to track trends across Anthropic models. Claude Opus 5.5 169.4
- Qwen in-house English automatic evaluation Only in system cards Models answer Qwen in-house English datasets on knowledge, comprehension, coding, math and related skills. Skills and weights change between reports.
Qwen2-72B 72.9%
- Recognition of model-written user turns (Anthropic) Only in system cards Models write synthetic user turns for real Claude Code transcripts, then judge which version is real. Score is accuracy above chance. Claude Mythos Preview 0.35
- LiveBench Dropped Models answer monthly refreshed questions across math, coding, reasoning, language, instruction following, and data analysis. Scored automatically against objective ground truth. Claude Fable 5.1 85.7%