最后更新
Dec 5, 2025, 11:21 PM
探索根据社区投票和性能指标排名的顶级AI模型
模型总数
87
数据库中可用
顶级模型
gemini-3-pro
排名第一
最高分
1314
最高评分
| # | 模型 | 评分 | 投票数 | 置信区间 | 组织 |
|---|---|---|---|---|---|
| 🥇 | gemini-3-pro | 1314.00 | 3,603 | ±12 | |
| 🥈 | gemini-2.5-pro | 1249.00 | 65,142 | ±7 | |
| 🥉 | gpt-5.1-high | 1248.00 | 1,505 | ±16 | OpenAI |
| 4 | gpt-5.1 | 1246.00 | 1,497 | ±16 | OpenAI |
| 5 | chatgpt-4o-latest-20250326 | 1237.00 | 17,102 | ±7 | OpenAI |
| 6 | gpt-4.5-preview-2025-02-27 | 1226.00 | 2,925 | ±11 | OpenAI |
| 7 | gemini-2.5-flash-preview-09-2025 | 1226.00 | 4,639 | ±11 | |
| 8 | gpt-5-chat | 1222.00 | 38,125 | ±8 | OpenAI |
| 9 | o3-2025-04-16 | 1218.00 | 44,890 | ±7 | OpenAI |
| 10 | gpt-4.1-2025-04-14 | 1216.00 | 40,396 | ±7 | OpenAI |
| 11 | gemini-2.5-flash | 1215.00 | 39,984 | ±7 | |
| 12 | Anthropicclaude-opus-4-20250514-thinking-16k | 1210.00 | 1,423 | ±15 | Anthropic |
| 13 | gpt-5-high | 1209.00 | 32,280 | ±8 | OpenAI |
| 14 | qwen3-vl-235b-a22b-instruct | 1206.00 | 4,841 | ±10 | Alibaba |
| 15 | Anthropicclaude-sonnet-4-20250514-thinking-32k | 1205.00 | 1,313 | ±16 | Anthropic |
| 16 | gpt-4.1-mini-2025-04-14 | 1202.00 | 39,495 | ±8 | OpenAI |
| 17 | o4-mini-2025-04-16 | 1202.00 | 40,020 | ±8 | OpenAI |
| 18 | ernie-5.0-preview-1120 | 1199.00 | 2,282 | ±13 | Baidu |
| 19 | Anthropicclaude-3-7-sonnet-20250219-thinking-32k | 1196.00 | 1,630 | ±15 | Anthropic |
| 20 | Tencenthunyuan-vision-1.5-thinking | 1194.00 | 2,734 | ±12 | Tencent |
| 21 | o1-2024-12-17 | 1193.00 | 3,694 | ±10 | OpenAI |
| 22 | qwen3-vl-235b-a22b-thinking | 1190.00 | 2,524 | ±13 | Alibaba |
| 23 | Anthropicclaude-opus-4-20250514 | 1189.00 | 2,516 | ±12 | Anthropic |
| 24 | gemini-2.5-flash-lite-preview-06-17-thinking | 1188.00 | 36,743 | ±8 | |
| 25 | Anthropicclaude-sonnet-4-20250514 | 1187.00 | 2,036 | ±13 | Anthropic |
| 26 | qwen-vl-max-2025-08-13 | 1184.00 | 3,313 | ±12 | Alibaba |
| 27 | gpt-5-mini-high | 1183.00 | 28,912 | ±9 | OpenAI |
| 28 | grok-4-0709 | 1181.00 | 31,159 | ±8 | xAI |
| 29 | gemini-1.5-pro-002 | 1178.00 | 8,916 | ±8 | |
| 30 | Anthropicclaude-3-7-sonnet-20250219 | 1178.00 | 4,661 | ±9 | Anthropic |
| 31 | gemini-2.5-flash-lite-preview-09-2025-no-thinking | 1177.00 | 4,704 | ±10 | |
| 32 | gemini-2.0-flash-001 | 1169.00 | 9,738 | ±7 | |
| 33 | gpt-4o-2024-05-13 | 1162.00 | 23,280 | ±8 | OpenAI |
| 34 | Anthropicclaude-3-5-sonnet-20241022 | 1162.00 | 10,532 | ±7 | Anthropic |
| 35 | glm-4.5v | 1157.00 | 3,478 | ±12 | Z.ai |
| 36 | mistral-medium-2505 | 1156.00 | 11,433 | ±9 | Mistral |
| 37 | Stepfunstep-1o-turbo-202506 | 1155.00 | 2,057 | ±14 | StepFun |
| 38 | gemma-3-27b-it | 1154.00 | 18,298 | ±9 | |
| 39 | mistral-medium-2508 | 1149.00 | 33,048 | ±8 | Mistral |
| 40 | Anthropicclaude-3-5-sonnet-20240620 | 1147.00 | 21,632 | ±9 | Anthropic |
| 41 | Tencenthunyuan-large-vision | 1147.00 | 1,466 | ±16 | Tencent |
| 42 | gpt-5-nano-high | 1147.00 | 4,100 | ±12 | OpenAI |
| 43 | Metallama-4-maverick-17b-128e-instruct | 1146.00 | 7,161 | ±9 | Meta |
| 44 | Stepfunstep-3 | 1141.00 | 3,441 | ±12 | StepFun |
| 45 | mistral-small-2506 | 1140.00 | 11,644 | ±10 | Mistral |
| 46 | gemini-1.5-flash-002 | 1139.00 | 7,256 | ±9 | |
| 47 | Anthropicclaude-3-5-haiku-20241022 | 1135.00 | 1,567 | ±15 | Anthropic |
| 48 | gemini-2.0-flash-lite-preview-02-05 | 1133.00 | 4,001 | ±10 | |
| 49 | mistral-small-3.1-24b-instruct-2503 | 1126.00 | 27,479 | ±9 | Mistral |
| 50 | Metallama-4-scout-17b-16e-instruct | 1126.00 | 6,631 | ±10 | Meta |
| 51 | Stepfunstep-1o-vision-32k-highres | 1124.00 | 2,844 | ±12 | StepFun |
| 52 | qwen2.5-vl-72b-instruct | 1122.00 | 3,767 | ±10 | Alibaba |
| 53 | gpt-4o-2024-08-06 | 1119.00 | 3,384 | ±12 | OpenAI |
| 54 | gemini-1.5-pro-001 | 1118.00 | 16,735 | ±11 | |
| 55 | qwen2.5-vl-32b-instruct | 1118.00 | 1,490 | ±15 | Alibaba |
| 56 | gpt-4-turbo-2024-04-09 | 1113.00 | 13,390 | ±11 | OpenAI |
| 57 | gpt-4o-mini-2024-07-18 | 1098.00 | 17,362 | ±7 | OpenAI |
| 58 | pixtral-large-2411 | 1094.00 | 5,439 | ±9 | Mistral |
| 59 | gpt-4.1-nano-2025-04-14 | 1089.00 | 1,211 | ±18 | OpenAI |
| 60 | qwen2-vl-72b | 1086.00 | 5,946 | ±9 | Alibaba |
| 61 | qwen-vl-max-1119 | 1086.00 | 1,431 | ±15 | Alibaba |
| 62 | gemini-1.5-flash-8b-001 | 1070.00 | 6,255 | ±10 | |
| 63 | Anthropicclaude-3-opus-20240229 | 1065.00 | 15,568 | ±10 | Anthropic |
| 64 | Stepfunstep-1v-32k | 1062.00 | 1,551 | ±16 | StepFun |
| 65 | gemini-1.5-flash-001 | 1060.00 | 13,261 | ±11 | |
| 66 | molmo-72b-0924 | 1048.00 | 3,063 | ±12 | AI2 |
| 67 | Tencenthunyuan-standard-vision-2024-12-31 | 1044.00 | 809 | ±21 | Tencent |
| 68 | Metallama-3.2-vision-90b-instruct | 1033.00 | 8,708 | ±8 | Meta |
| 69 | qwen2-vl-7b-instruct | 1032.00 | 5,778 | ±10 | Aliaba |
| 70 | pixtral-12b-2409 | 1025.00 | 7,520 | ±9 | Mistral |
| 71 | internvl2-26b | 1025.00 | 5,146 | ±12 | OpenGVLab |
| 72 | amazon-nova-lite-v1.0 | 1021.00 | 1,856 | ±15 | Amazon |
| 73 | amazon-nova-pro-v1.0 | 1021.00 | 2,338 | ±13 | Amazon |
| 74 | Anthropicclaude-3-sonnet-20240229 | 1020.00 | 12,314 | ±11 | Anthropic |
| 75 | 01.AIyi-vision | 1005.00 | 1,220 | ±18 | 01 AI |
| 76 | Anthropicclaude-3-haiku-20240307 | 1003.00 | 13,380 | ±12 | Anthropic |
| 77 | Coherec4ai-aya-vision-32b | 1001.00 | 847 | ±22 | Cohere |
| 78 | molmo-7b-d-0924 | 997.00 | 2,828 | ±13 | AI2 |
| 79 | Metallama-3.2-vision-11b-instruct | 991.00 | 4,818 | ±11 | Meta |
| 80 | Nvidianvila-internal-15b-v1 | 988.00 | 1,078 | ±20 | NVIDIA |
| 81 | llava-onevision-qwen2-72b-ov | 981.00 | 1,321 | ±18 | LLaVA |
| 82 | llava-v1.6-34b | 967.00 | 4,531 | ±12 | LLaVA |
| 83 | minicpm-v-2_6 | 965.00 | 1,987 | ±15 | OpenBMB |
| 84 | cogvlm2-llama3-chat-19b | 964.00 | 1,991 | ±15 | Zhipu AI |
| 85 | internvl2-4b | 958.00 | 3,706 | ±12 | OpenGVLab |
| 86 | Azurephi-3.5-vision-instruct | 922.00 | 2,592 | ±15 | Microsoft |
| 87 | Azurephi-3-vision-128k-instruct | 884.00 | 1,401 | ±18 | Microsoft |
数据每小时更新 • 显示 87 个模型
数据来源：LM BASE 排行榜