单项能力冠军
8 个维度最高分模型 · 点击卡片直达对应榜单
智能体最强
Claude Fable 5.2
90.06分 · Anthropic
编程最强
Claude Fable 5.2
86.31分 · Anthropic
推理最强
Claude Fable 5.2
89.93分 · Anthropic
多模态最强
Claude Fable 5.2
89.35分 · Anthropic
知识最强
Claude Fable 5.2
97.41分 · Anthropic
多语言最强
Qwen3.7 Max
100分 · Alibaba
指令遵循最强
Grok 4.3
97.1分 · xAI
数学最强
Claude Fable 5.2
93.8分 · Anthropic
| 排名 | 模型 / 厂商 | 类型 | 综合 | 智能体 | 编程 | 推理 | 多模态 | 知识 | 多语言 | 指令 | 数学 | 输入 $/1M | 输出 $/1M | 上下文 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 Anthropic |
闭源 | 91.41 | 90.06 | 86.31 | 89.93 | 89.35 | 97.41 | — | — | 93.8 | $8 | $40 | 1M |
| 2 | Gemini 4 Carbon |
闭源 | 87.91 | — | 80.52 | 83.37 | — | — | — | — | 93.3 | $2 | $10 | — |
| 3 | Claude Opus 5.5 Anthropic |
闭源 | 85.77 | 89.34 | 82.4 | 79.95 | 84.44 | 88.17 | — | — | 93.3 | $4 | $20 | 1M |
| 4 | GPT-6 Astra OpenAI |
闭源 | 84.98 | 73.52 | 73.91 | 80.43 | 78.93 | 83.81 | — | — | 93.8 | $10 | $50 | — |
| 5 | GPT-6.1 Sol OpenAI |
闭源 | 84.91 | 75.56 | 69.28 | 79.94 | 78.36 | 84.13 | — | — | 93.8 | $2 | $10 | — |
| 6 | Gemini 4 Argon |
闭源 | 81.38 | 77.59 | 71.95 | 77.32 | — | 79.36 | — | — | 87.4 | $2 | $10 | — |
| 7 | Claude Sonnet 5.5 Anthropic |
闭源 | 81.24 | 68.27 | 81.41 | 76.1 | 77.65 | 79.9 | — | — | 89.7 | $2 | $10 | 1M |
| 8 | Claude Fable 5.1 Anthropic |
闭源 | 80.82 | 80.35 | 76.34 | 76.78 | 81.2 | 84.7 | — | — | 92 | $10 | $50 | 1M |
| 9 | Claude Fable 5 Anthropic |
闭源 | 80.38 | 74.02 | 70.97 | 72.03 | 75.26 | 80.16 | — | 77.1 | 90.4 | $10 | $50 | 1M |
| 10 | GPT-6.1 Terra OpenAI |
闭源 | 80.13 | 76.01 | — | 75.3 | 77.22 | 76.47 | — | — | 92.9 | $1 | $5 | — |
| 11 | Claude Opus 5 Anthropic |
闭源 | 79.04 | 76.98 | 70.3 | 74.7 | 77.78 | 80.31 | — | — | 86.2 | $5 | $25 | 1M |
| 12 | GPT-6 Sol OpenAI |
闭源 | 77.65 | 57.66 | 64.68 | 72.03 | 74.61 | 78.67 | — | — | 92.1 | $2 | $10 | — |
| 13 | Kimi K3.1 Pro Moonshot AI |
开源 | 74.64 | 72.72 | — | 70.57 | 73.91 | 74.53 | — | — | — | $2 | $10 | — |
| 14 | GPT-5.6 Sol OpenAI |
闭源 | 74.37 | 67.86 | 67.18 | 73.72 | 75.48 | 75.52 | — | 89.1 | 90.3 | $4 | $20 | — |
| 15 | GPT-5.5 Pro OpenAI |
闭源 | 72.44 | — | — | 75.04 | — | — | — | — | 88.5 | $30 | $180 | — |
| 16 | GPT-5.6 Terra OpenAI |
闭源 | 69.45 | 60.34 | 61.8 | 69.18 | 69 | 68.3 | — | 87.1 | 84.8 | $2 | $12 | — |
| 17 | Claude Opus 4.8 Anthropic |
闭源 | 69.22 | 59.52 | 60.3 | 64.87 | 67.45 | 69.47 | — | 75.4 | 79.3 | $5 | $25 | 1M |
| 18 | Kimi K3 Moonshot AI |
开源 | 69.20 | 66.61 | 58.8 | 65.12 | 66.94 | 66.77 | — | — | — | $3 | $15 | — |
| 19 | Muse Wonder Full Meta |
闭源 | 69.07 | — | 70.79 | 75.88 | — | 73.74 | — | — | — | — | — | — |
| 20 | GPT-5.5 OpenAI |
闭源 | 68.39 | 59.5 | 62.15 | 66.64 | 68.21 | 70.15 | — | 93.3 | 85.9 | $5 | $30 | — |
| 21 | Claude Opus 4.7 (Adaptive) Anthropic |
闭源 | 68.06 | 56.75 | 55.48 | — | 62.33 | 64.67 | — | — | — | $5 | $25 | 1M |
| 22 | GPT-5.4 Pro OpenAI |
闭源 | 67.89 | — | — | 72.57 | — | — | — | — | 81.4 | $30 | $180 | — |
| 23 | Gemini 3.8 Flash |
闭源 | 66.61 | 64.68 | 59.94 | 64.47 | 70.39 | 69.16 | — | — | 65.4 | $0.75 | $3.75 | — |
| 24 | Grok 4.6 xAI |
闭源 | 66.47 | 69.74 | 58.56 | 65.03 | — | 67.93 | — | — | 65.6 | $2 | $6 | — |
| 25 | Gemini 3.7 Flash |
闭源 | 66.21 | 60.89 | 57.66 | 62.88 | 70.12 | 70.19 | — | — | 70.2 | $0.75 | $3.75 | — |
| 26 | Claude Haiku 5.5 Anthropic |
闭源 | 66.17 | 60.72 | 51.66 | 58.13 | 60.71 | 63.44 | — | — | 74.3 | $0.1 | $0.5 | 1M |
| 27 | GPT-5.2 Pro OpenAI |
闭源 | 66.13 | — | — | — | — | — | — | — | — | $21 | $168 | — |
| 28 | GPT-5.4 OpenAI |
闭源 | 66.09 | 53.13 | 47.94 | 62.65 | 65 | 67.16 | — | 90.7 | 77.1 | $2.5 | $15 | — |
| 29 | Muse Spark 1.1 Meta |
闭源 | 65.44 | 57.93 | 52.71 | 58.77 | — | 67.1 | — | — | — | — | — | — |
| 30 | Muse Spark 1.2 Meta |
闭源 | 65.35 | 59.32 | 52.96 | 61.34 | — | 64.13 | — | — | — | $1.25 | $4.25 | — |
| 31 | Ling 3.1 Flash InclusionAI |
开源 | 65.26 | 63 | 58.05 | 61.65 | — | — | — | — | — | — | — | — |
| 32 | DeepSeek V4.1 Flash 1017 DeepSeek |
开源 | 65.13 | 61.84 | 63.11 | 58.71 | 63.95 | 63.72 | — | — | 65.6 | $0.3 | $1.2 | 1M |
| 33 | Claude Opus 4.7 Anthropic |
闭源 | 64.93 | 54.22 | 55.23 | 59.66 | — | 64.42 | — | — | 68.3 | $5 | $25 | 1M |
| 34 | Qwen3.8 Max Alibaba |
开源 | 64.71 | 65.93 | 52.98 | 60.82 | 66 | 65.37 | — | 94.7 | 74.1 | — | — | — |
| 35 | Gemini 3.1 Pro |
闭源 | 64.26 | 40.84 | 39.39 | 56.96 | 65.69 | 66.58 | — | 90.2 | 60.6 | $2 | $12 | — |
| 36 | Claude Sonnet 5 Anthropic |
闭源 | 64.23 | 64.25 | 57.23 | 61.55 | 61.91 | 63.3 | — | — | 64.9 | $2 | $10 | 1M |
| 37 | dots3-note Preview Dots Studio |
开源 | 63.77 | 59.82 | — | — | 65.28 | — | — | 89.1 | — | $0 | $0 | 512K |
| 38 | GPT-5.6 Luna OpenAI |
闭源 | 63.72 | 59.05 | 61.93 | 58.28 | 65.36 | 63.08 | — | — | 78.9 | $0.2 | $1.2 | — |
| 39 | Muse Wonder Meta |
闭源 | 63.03 | — | 65.5 | 69.34 | — | 68.4 | — | — | — | $4 | $20 | — |
| 40 | Grok 4.5 xAI |
闭源 | 62.84 | 61.03 | 55.19 | 57.91 | — | 65.75 | — | — | 58.5 | $2 | $6 | — |
| 41 | Sage-A1.5 InternScience |
开源 | 62.64 | 58.43 | 55.06 | 59.46 | — | — | — | 91.9 | — | $0 | $0 | — |
| 42 | DeepSeek V4 Pro 0813 DeepSeek |
开源 | 62.43 | 55.05 | 47.86 | 58.06 | — | 62.54 | — | — | 84.4 | $1.32 | $3.96 | 1M |
| 43 | Gemini 3.6 Flash |
闭源 | 62.38 | 52.57 | 51.58 | 55.05 | 65.83 | 64.3 | — | — | 59.2 | $0.75 | $3.75 | — |
| 44 | GPT-6 Luna OpenAI |
闭源 | 62.37 | 53.79 | 51.63 | 54.36 | 63.89 | 62.33 | — | — | 78.7 | $0.1 | $0.5 | — |
| 45 | GPT-5.3 Codex OpenAI |
闭源 | 62.31 | 56.22 | 53.32 | 58.25 | — | 63.62 | — | 92.6 | — | $1.75 | $14 | — |
| 46 | Ornith-1.5-397B Ornith AI |
开源 | 62.19 | 59.44 | 54.69 | — | — | 64.17 | — | — | — | $0 | $0 | — |
| 47 | Qwen3.7 Max Alibaba |
闭源 | 62.09 | 41.04 | 44.71 | 51.39 | — | 59.75 | 100 | 92.8 | 78.3 | — | — | — |
| 48 | Claude Opus 4.6 Anthropic |
闭源 | 61.95 | 46.32 | 46.33 | 56.47 | 55.72 | 58.15 | — | 52.4 | 64.7 | $5 | $25 | 1M |
| 49 | Gemini 3.5 Flash |
闭源 | 61.48 | 51.1 | 50.95 | 52.35 | 68.64 | 65.2 | — | 87.7 | 62.6 | $1.5 | $9 | — |
| 50 | GLM-5.3 Z.AI |
开源 | 61.17 | 67.84 | 55.36 | 56.65 | — | 58.66 | — | — | 67 | $0 | $0 | — |
| 51 | Hy4 preview Tencent |
开源 | 61.02 | 56.77 | 56.59 | — | — | 63.64 | — | — | — | $0 | $0 | — |
| 52 | Gemini 3 Pro |
闭源 | 60.77 | — | 44.38 | 48.36 | 58.39 | 59.46 | — | 86.1 | — | $2 | $12 | — |
| 53 | MiniMax M3.1 Flash MiniMax |
闭源 | 60.06 | 55.64 | 53.92 | 55.09 | 64.57 | 63.8 | — | — | — | $0.15 | $0.6 | — |
| 54 | GLM-5.2 Z.AI |
开源 | 60.05 | 55.51 | 53.97 | 42.85 | — | 56.46 | — | 89.9 | 74.6 | $1.4 | $4.4 | — |
| 55 | Muse Spark Meta |
闭源 | 59.95 | 49.94 | 50.03 | 52.79 | 61.55 | 61.66 | — | 93.3 | — | — | — | — |
| 56 | GPT-5.2 OpenAI |
闭源 | 59.49 | 44.9 | 37.43 | 50.19 | 58.72 | 58.44 | — | 92.6 | 66.5 | $1.75 | $14 | — |
| 57 | GLM-5.3-Flash Z.AI |
开源 | 57.93 | 58.23 | 48.45 | 49.82 | 64.45 | 60.19 | — | — | 56.2 | $0 | $0 | — |
| 58 | Inkling 2 Small Thinking Machines Lab |
闭源 | 57.45 | 59.87 | 59.16 | — | 63 | 59.63 | — | — | 85.9 | $0.3 | $1 | — |
| 59 | Kimi K2.6 Moonshot AI |
开源 | 57.41 | 44.34 | 43.18 | 47.76 | 59.2 | 58.59 | — | 83.5 | 73.2 | $0.95 | $4 | — |
| 60 | MiMo-V2.6-Pro Xiaomi |
开源 | 57.15 | 56.19 | 57.38 | 62.56 | — | 61.59 | — | — | — | $0.435 | $0.87 | — |
| 61 | GPT-5.1 OpenAI |
闭源 | 56.88 | — | 36.7 | 45.58 | — | 52.49 | — | 89.4 | — | $1.25 | $10 | — |
| 62 | Step 5 Preview StepFun |
开源 | 56.66 | 54.92 | 49.08 | 52.55 | 59.51 | 60.28 | — | — | — | $1 | $2.7 | — |
| 63 | GPT-5.2-Codex OpenAI |
闭源 | 56.35 | 44.86 | 44.74 | 43.78 | — | 56.81 | — | 93.8 | — | $1.75 | $14 | — |
| 64 | Muse Ember Meta |
闭源 | 56.29 | — | — | — | — | — | — | — | — | $0.1 | $0.5 | — |
| 65 | Grok 4.20 xAI |
闭源 | 56.16 | 25.68 | 22.41 | — | 55.31 | 52.87 | — | — | — | $1.25 | $2.5 | — |
| 66 | GLM-5.1 Z.AI |
开源 | 56.00 | 45.33 | 47.52 | 44.84 | — | 51.62 | — | 93.8 | 55.7 | $1.4 | $4.4 | — |
| 67 | Kimi K2.5 (Reasoning) Moonshot AI |
开源 | 55.82 | 40.44 | — | — | 51.73 | 48.57 | — | — | — | $0.6 | $3 | — |
| 68 | Qwen3.8-Flash-Next Alibaba |
开源 | 55.72 | 63.05 | 50.66 | 55.43 | 60.19 | 55.9 | — | 91.2 | — | $0 | $0 | — |
| 69 | Claude Sonnet 4.6 Anthropic |
闭源 | 55.52 | 46.61 | 45.03 | 49.68 | 53.17 | 54.31 | — | 48 | — | $3 | $15 | 200K |
| 70 | MiMo-V2.5-Pro Xiaomi |
闭源 | 55.40 | 43.34 | 43.54 | 45.68 | — | 51.39 | — | 93.8 | — | — | — | — |
| 71 | Qwen 3.6 Max (preview) Alibaba |
闭源 | 55.17 | — | 43.35 | — | — | — | — | — | — | — | — | — |
| 72 | MiMo-V2-Pro Xiaomi |
闭源 | 55.15 | — | 40.27 | 43.02 | — | 48.72 | — | 84 | — | — | — | — |
| 73 | MiMo-V2.6-Flash Xiaomi |
开源 | 55.14 | 49.19 | 56.3 | 47.2 | — | 52.45 | — | — | — | $0.14 | $0.28 | — |
| 74 | Qwen3.5 397B Alibaba |
开源 | 55.11 | 45.17 | — | — | 53.81 | 51.92 | 93.8 | 79.9 | 72.7 | $0.6 | $3.6 | — |
| 75 | GLM-5 Z.AI |
开源 | 54.43 | 43.08 | 39.68 | 42.41 | — | 49.52 | 89.5 | 88.6 | 72.5 | $1 | $3.2 | — |
| 76 | Qwen3.8-27B Alibaba |
开源 | 54.37 | 62.98 | 46.83 | 42.91 | 60.17 | 49.05 | — | 86.9 | — | $0 | $0 | — |
| 77 | Gemini 3 Flash |
闭源 | 53.95 | 34.32 | 32.85 | 45.62 | 63.83 | 56.56 | — | 66.1 | 53.3 | $0.5 | $3 | — |
| 78 | Claude Opus 4.5 Thinking Anthropic |
闭源 | 53.70 | — | — | 44.46 | — | 54.11 | — | 69.9 | — | — | — | — |
| 79 | Claude Opus 4.5 Anthropic |
闭源 | 53.65 | 34.21 | 42.3 | 41.15 | 49.42 | 50.01 | 96.5 | 31.9 | 52.9 | $5 | $25 | 200K |
| 80 | Qwen3.7 Plus Alibaba |
闭源 | 53.62 | 35.87 | 40.92 | 45.87 | 55.8 | 52.78 | 95.7 | 92.8 | 60.1 | — | — | — |
| 81 | GPT-5.1-Codex OpenAI |
闭源 | 53.61 | — | 37.08 | 44.94 | — | 52.22 | — | 85.6 | — | $1.25 | $10 | — |
| 82 | Kimi K2.7 Code Moonshot AI |
开源 | 53.60 | 39.68 | 42.33 | 48.43 | — | 54.68 | — | 76.6 | 54.2 | $0.95 | $4 | — |
| 83 | Ternary Bonsai 2 27B Prism ML |
开源 | 53.53 | — | — | — | — | — | — | 74 | 82.6 | $0 | $0 | — |
| 84 | GLM-5-Turbo Z.AI |
闭源 | 53.40 | — | — | 41.51 | — | 47.8 | — | 89.8 | — | $1.2 | $4 | — |
| 85 | Qwen3.6 Plus Alibaba |
闭源 | 53.37 | 34.84 | 40.34 | 35.15 | 54.55 | 52.17 | 93.8 | 85.8 | 62.3 | — | — | — |
| 86 | GPT-5.4 mini OpenAI |
闭源 | 53.12 | 36.2 | 35.58 | 30.1 | — | 50.53 | — | 89.9 | 51.9 | $0.75 | $4.5 | — |
| 87 | Apodex 1.1 Apodex |
闭源 | 52.82 | 50.94 | 47.79 | 48.84 | — | 55.15 | — | — | — | — | — | — |
| 88 | Grok 4.3 xAI |
闭源 | 52.75 | 28.08 | 26.89 | 34.2 | — | 53.7 | — | 97.1 | 47.4 | $1.25 | $2.5 | — |
| 89 | Kimi K2.5 Moonshot AI |
开源 | 52.73 | 42.21 | 40.43 | 43.41 | 53.25 | 50.62 | 87.3 | 85.8 | 73.5 | $0.6 | $3 | — |
| 90 | Hy3 Preview Tencent |
开源 | 52.71 | — | 34.01 | — | — | 46.73 | — | 48.4 | — | $0 | $0 | — |
| 91 | Qwen3.5-122B-A10B Alibaba |
开源 | 52.64 | 33.43 | 35.4 | 40.21 | 51.4 | 47.96 | 87.1 | 93 | — | $0 | $0 | — |
| 92 | MAI-Thinking-1 Microsoft |
闭源 | 52.56 | — | — | — | — | 54.76 | — | 94.7 | 69.1 | — | — | — |
| 93 | Mistral Large 4 Mistral |
开源 | 52.08 | 44.66 | 44.94 | 45.77 | — | — | — | — | — | $0.7 | $2.1 | — |
| 94 | Grok 4 xAI |
闭源 | 51.44 | — | — | 41.32 | — | 49.52 | — | 64.3 | — | — | — | — |
| 95 | Muse Spark Open Meta |
开源 | 51.16 | 51.89 | 51.35 | 47.96 | — | 56.64 | — | — | — | — | — | — |
| 96 | DeepSeek V3.2 DeepSeek |
开源 | 49.96 | — | 30.8 | 36.09 | — | 41.39 | — | 58.2 | — | $0.28 | $0.42 | 128K |
| 97 | Inkling-Small Thinking Machines Lab |
开源 | 49.95 | 35.9 | 37.09 | 43.75 | 51.66 | 50.68 | — | 93.3 | 64.6 | $0.58 | $1.44 | — |
| 98 | MiMo-V2-Omni Xiaomi |
闭源 | 49.57 | — | — | 38.57 | — | 43.31 | — | 64 | — | — | — | — |
| 99 | MiniMax M2.5 MiniMax |
闭源 | 49.51 | 30.83 | 34.75 | — | — | — | — | — | — | $0.3 | $1.2 | — |
| 100 | Qwen3.5 Plus Alibaba |
闭源 | 49.28 | — | — | — | — | — | — | — | — | $0.4 | $2.4 | — |
| 101 | GLM-5V-Turbo Z.AI |
闭源 | 49.28 | — | 34.42 | 38.82 | — | 45.2 | — | 74 | — | $1.2 | $4 | — |
| 102 | Nemotron 3.5 Super VL 120B A12B NVIDIA |
开源 | 49.17 | 45.74 | — | 46 | — | 51.29 | — | 66.6 | — | — | — | — |
| 103 | MiniMax M3 MiniMax |
开源 | 49.03 | 39.21 | 37.66 | 38.19 | 53.34 | 54.21 | — | 93.8 | — | $0.3 | $1.2 | — |
| 104 | Gemini 2.5 Pro |
闭源 | 48.92 | 29.67 | 23.29 | 37.13 | — | 44.65 | — | 57.8 | 33.2 | $1.25 | $10 | — |
| 105 | GLM-4.7 Z.AI |
开源 | 48.59 | 33.96 | 37.77 | 36.49 | — | 43.19 | — | 82.8 | — | $0 | $0 | — |
| 106 | Qwen3.5-27B Alibaba |
开源 | 48.30 | 38.89 | 34.16 | 39.47 | 50.38 | 44.8 | 87.1 | 92.9 | — | $0 | $0 | — |
| 107 | Qwen3.6-27B Alibaba |
开源 | 48.30 | 29.74 | 35.7 | 31.39 | 51.04 | 46.32 | — | 82.4 | 56.2 | $0 | $0 | — |
| 108 | GPT-5 mini OpenAI |
闭源 | 48.14 | 31.32 | 29.25 | — | — | — | — | — | — | $0.25 | $2 | — |
| 109 | Inkling Thinking Machines Lab |
开源 | 48.08 | 36.7 | 33.62 | 37.71 | 49.99 | 50.39 | — | 87.6 | 54.6 | $1.87 | $4.68 | — |
| 110 | MiniMax M2.7 MiniMax |
开源 | 47.73 | 33.05 | 35 | 38.83 | — | 45.41 | — | 93 | 46.6 | $0.3 | $1.2 | — |
| 111 | Qwen3.7 Flash Alibaba |
闭源 | 47.45 | — | — | — | — | — | — | — | 33.5 | $0.03 | $0.13 | — |
| 112 | Claude Sonnet 4.5 Anthropic |
闭源 | 47.18 | 36.12 | — | — | — | — | — | — | 32.7 | $3 | $15 | 200K |
| 113 | Gemini 3.5 Flash-Lite |
闭源 | 46.77 | 35.28 | 35.59 | 9.07 | 51.29 | 46.03 | — | — | 34.1 | $0.3 | $2.5 | — |
| 114 | Nemotron 3 Ultra NVIDIA |
开源 | 46.53 | 25.07 | 22.65 | 39.28 | — | 49.68 | 89.2 | 92.1 | — | $0 | $0 | — |
| 115 | Gemini 3.1 Flash-Lite |
闭源 | 46.52 | 30.43 | 29.31 | — | 49.53 | 45.78 | — | — | 40.2 | $0.25 | $1.5 | — |
| 116 | GPT-5.4 nano OpenAI |
闭源 | 46.51 | 33.31 | 30.17 | 37.65 | 38.78 | 38.94 | — | 93.3 | 48.3 | $0.2 | $1.25 | — |
| 117 | GPT-5 (medium) OpenAI |
闭源 | 45.96 | — | 34.33 | 39.28 | — | 48.14 | — | 86.4 | — | — | — | — |
| 118 | Ling 3.0 Flash InclusionAI |
开源 | 45.81 | 34.33 | 32.88 | 38.07 | — | 42.64 | — | 75.2 | 71.2 | — | — | — |
| 119 | Qwen3.5-35B-A3B Alibaba |
开源 | 45.47 | 35.64 | 28.19 | 37.03 | 47.65 | 42.28 | 83.8 | 88.8 | — | $0 | $0 | — |
| 120 | Grok 4.1 Fast (Reasoning) xAI |
闭源 | 45.46 | — | 27.3 | 36.15 | — | 42.21 | — | 63 | — | — | — | — |
| 121 | Step 3.7 Flash StepFun |
开源 | 45.39 | 40.48 | 34.08 | 38.6 | — | 45.28 | — | 82.1 | — | $0.2 | $1.15 | — |
| 122 | o3 OpenAI |
闭源 | 45.03 | — | — | 40.44 | — | 47.17 | — | 87.4 | 44.7 | $2 | $8 | — |
| 123 | o3-pro OpenAI |
闭源 | 44.99 | — | — | — | — | — | — | — | — | $20 | $80 | — |
| 124 | Grok 3 Mini xAI |
闭源 | 44.09 | — | — | — | — | — | — | — | — | $0.3 | $0.5 | — |
| 125 | Beam 1.0 501B-A23B Reflection AI |
开源 | 43.82 | 44.92 | 30.75 | 39.34 | — | 48.61 | — | — | — | — | — | 1M |
| 126 | Trinity-Large-Thinking Arcee AI |
开源 | 43.77 | 24.41 | 20.2 | 31.13 | — | 37.71 | — | 28.9 | — | $0.25 | $0.9 | — |
| 127 | Grok 4 Fast (Reasoning) xAI |
闭源 | 43.30 | — | 23.43 | 34.23 | — | 40.26 | — | 60.1 | — | — | — | — |
| 128 | Qwen3.6-35B-A3B Alibaba |
开源 | 42.87 | 34.15 | 35.77 | 36.93 | 38.06 | 42.72 | — | 78.3 | 48.2 | — | — | — |
| 129 | Nemotron 3.5 Bolt 74B-A9B NVIDIA |
开源 | 42.64 | 38.45 | — | 39.27 | — | — | — | — | — | — | — | — |
| 130 | Step 3.5 Flash StepFun |
开源 | 42.45 | — | — | — | — | — | — | — | — | $0.1 | $0.3 | — |
| 131 | Qwen3.5 Flash Alibaba |
闭源 | 42.31 | — | 28.42 | — | — | 43.71 | — | — | 32.6 | $0.1 | $0.4 | — |
| 132 | Gemini 2.5 Flash |
闭源 | 41.93 | — | — | 30.01 | — | 36.53 | — | 45.1 | — | $0.3 | $2.5 | — |
| 133 | GLM-4.6 Z.AI |
开源 | 41.69 | — | 28.1 | 32.38 | — | 36.86 | — | 42.1 | — | — | — | — |
| 134 | Gemma 4 26B A4B |
开源 | 41.36 | — | 31.92 | 35.24 | 48.67 | 41.41 | — | 88.7 | — | $0 | $0 | — |
| 135 | DeepSeek-R1 DeepSeek |
开源 | 40.82 | — | — | 31.15 | — | 40.41 | — | 45.9 | — | $0.55 | $2.19 | — |
| 136 | Grok 3 [Beta] xAI |
闭源 | 40.59 | — | — | — | — | 40.82 | — | — | — | — | — | — |
| 137 | DeepSeek V3.1 DeepSeek |
开源 | 40.47 | — | — | 30.87 | — | 37.54 | — | 43.5 | — | $0 | $0 | 128K |
| 138 | Claude 4.1 Opus Anthropic |
闭源 | 40.35 | — | — | — | — | — | — | — | — | $15 | $75 | 200K |
| 139 | Spark-X2.6-4B SparkLLM |
开源 | 40.34 | 35.71 | 33.22 | — | — | 43.1 | — | 78.2 | 60.9 | $0 | $0 | — |
| 140 | MiMo-V2-Flash Xiaomi |
开源 | 40.19 | — | 31.39 | 30.97 | — | 33.61 | — | 46.3 | — | $0 | $0 | — |
| 141 | Claude Haiku 4.5 Anthropic |
闭源 | 39.97 | 23.39 | 18.52 | — | — | 34.82 | — | — | — | $1 | $5 | 200K |
| 142 | Qwen3 Max Alibaba |
闭源 | 39.44 | — | — | 33.15 | — | 39.19 | — | 51.8 | — | — | — | — |
| 143 | DeepSeek V3.1 (Reasoning) DeepSeek |
开源 | 39.40 | — | — | 32.05 | — | 40.22 | — | 48.4 | — | $0 | $0 | 128K |
| 144 | o3-mini OpenAI |
闭源 | 39.30 | — | — | — | — | 37 | — | — | — | $1.1 | $4.4 | — |
| 145 | GLM-4.7-Flash Z.AI |
开源 | 38.94 | — | — | — | — | — | — | — | — | $0 | $0 | — |
| 146 | Claude 4.1 Opus Thinking Anthropic |
闭源 | 38.94 | — | — | 37.21 | — | 43.6 | — | 66.5 | — | — | — | 200K |
| 147 | o1 OpenAI |
闭源 | 38.52 | — | 30.73 | 33.23 | — | 40.73 | — | 86 | 29.8 | $15 | $60 | — |
| 148 | Claude 4 Sonnet Anthropic |
闭源 | 38.43 | — | — | 31.96 | — | 37.31 | — | 53.5 | — | $3 | $15 | 200K |
| 149 | K-Exaone LG AI Research |
闭源 | 38.02 | — | 26.08 | 29.95 | — | 35.52 | — | 78.7 | — | — | — | — |
| 150 | GPT-4.1 OpenAI |
闭源 | 37.31 | — | — | 28.25 | — | 34.65 | 61.5 | 50.3 | 23.4 | $2 | $8 | — |
| 151 | o1-pro OpenAI |
闭源 | 37.24 | — | — | — | — | — | — | — | — | $150 | $600 | — |
| 152 | GPT-5 nano OpenAI |
闭源 | 37.07 | — | — | — | — | — | — | — | — | $0.05 | $0.4 | — |
| 153 | GPT-OSS 20B OpenAI |
开源 | 37.05 | 24.34 | 25.48 | 31.31 | — | 35.86 | — | 79.2 | — | $0 | $0 | — |
| 154 | LFM2.5-24B-A2B LiquidAI |
开源 | 36.76 | 32.71 | — | — | — | 39.64 | — | 75.6 | — | $0.1 | $1 | — |
| 155 | Grok 4.1 Fast xAI |
闭源 | 36.41 | — | — | 25.45 | — | 30.87 | — | 41.9 | — | $0.2 | $0.5 | — |
| 156 | DeepSeek V3 0324 DeepSeek |
开源 | 36.21 | — | — | 26.5 | — | 33.45 | 55.5 | 47.7 | — | — | — | 128K |
| 157 | Ornith-1.5-35B-A3B Ornith AI |
开源 | 35.93 | 32.09 | 28.18 | — | — | 39.62 | — | — | — | $0 | $0 | — |
| 158 | o1-preview OpenAI |
闭源 | 35.72 | — | 23.21 | — | — | — | — | — | — | $15 | $60 | — |
| 159 | Gemma 4 12B |
开源 | 35.22 | — | 28.27 | 32.25 | — | 37.89 | — | 90.1 | 57.8 | — | — | — |
| 160 | GLM-4.5-Air Z.AI |
闭源 | 35.02 | — | — | 26.05 | — | 31.82 | — | 43.3 | — | $0.2 | $1.1 | — |
| 161 | Mistral Large 3 Mistral |
开源 | 34.16 | 17.57 | 16.47 | 24.66 | — | 31.95 | — | 41.5 | — | $0.5 | $1.5 | — |
| 162 | ZAYA1-8B Zyphra |
开源 | 34.03 | — | — | — | — | 37.41 | — | 23.6 | 44.3 | $0 | $0 | — |
| 163 | Grok Code Fast 1 xAI |
闭源 | 33.93 | — | 19.88 | 29.13 | — | 35.45 | — | 48.2 | — | $0.2 | $1.5 | — |
| 164 | Mercury 2.5 Inception |
闭源 | 33.69 | 14.73 | 22.36 | 30.25 | — | 35.05 | — | 81.1 | — | $0.04 | $0.15 | — |
| 165 | Nemotron 3 Nano Omni 30B A3B NVIDIA |
开源 | 33.64 | — | 23.79 | 30.22 | 37.68 | 34.04 | — | 75.4 | — | $0 | $0 | — |
| 166 | Ornith-1.5-9B Ornith AI |
开源 | 33.60 | 28.31 | — | — | — | 37.2 | — | — | — | $0 | $0 | — |
| 167 | Kimi K2 Moonshot AI |
闭源 | 33.57 | — | — | 28.7 | — | 35.72 | — | 48.4 | — | $0.6 | $2.5 | — |
| 168 | Ling 2.6 Flash InclusionAI |
开源 | 33.50 | — | 20.21 | 24.4 | — | 30.16 | — | 38.6 | — | — | — | — |
| 169 | Mercury 2 Inception |
闭源 | 33.44 | 17.52 | 17.11 | — | — | — | — | — | — | $0.25 | $0.75 | — |
| 170 | Muse Glimmer 30B Meta |
开源 | 32.62 | 19.74 | 24.58 | 28.29 | 41.74 | 37.79 | — | 81.1 | 81.1 | $0 | $0 | — |
| 171 | GPT-OSS 120B OpenAI |
开源 | 32.04 | 20.01 | 22.23 | 27.24 | — | 36.05 | — | 84.3 | — | $0 | $0 | — |
| 172 | DeepSeek V3 DeepSeek |
开源 | 31.69 | 15.73 | 18.09 | 25.21 | — | 31.1 | — | 39.6 | — | $0.27 | $1.1 | 128K |
| 173 | Solar Pro 3 Upstage |
闭源 | 31.21 | — | — | 23.07 | — | 30.38 | — | 87.1 | — | $0.15 | $0.6 | — |
| 174 | DeepSeek R1 Distill Qwen 32B DeepSeek |
开源 | 31.03 | — | — | — | — | 29.55 | — | 28.8 | — | $0 | $0 | 128K |
| 175 | Sarvam 105B Sarvam |
开源 | 30.52 | — | — | 27.3 | — | 33.75 | — | 39.1 | — | $0 | $0 | — |
| 176 | GPT-4o OpenAI |
闭源 | 30.49 | — | — | 22.02 | — | 27.74 | 30.2 | 39 | 23.4 | $2.5 | $10 | — |
| 177 | Solar Pro 2 Upstage |
闭源 | 30.46 | — | — | 21.32 | — | 27.64 | — | 38.2 | — | — | — | — |
| 178 | Command A+ Cohere |
开源 | 29.87 | 14.62 | 17.26 | 21.32 | 33.48 | 27.44 | — | 90.7 | — | $2.5 | $10 | 128K |
| 179 | Mistral Medium 3.5 128B Mistral |
开源 | 29.70 | 21.28 | 21.62 | 23.76 | — | 28.62 | — | 84 | — | $1.5 | $7.5 | — |
| 180 | Celeris-1 Celeris |
闭源 | 29.27 | 20.09 | 20.54 | 26.56 | — | 31.52 | — | — | — | $0.2 | $0.7 | 128K |
| 181 | Gemma 4 31B |
开源 | 29.10 | 13.48 | 30.26 | 32.52 | 47.51 | 36.99 | — | 92.9 | — | $0 | $0 | — |
| 182 | Mistral Large 2 Mistral |
闭源 | 29.09 | — | — | — | — | 28.86 | — | 34.9 | — | — | — | — |
| 183 | GPT-4.1 mini OpenAI |
闭源 | 29.07 | — | 19.73 | 24.74 | — | 30.51 | — | 44.2 | 23.4 | $0.4 | $1.6 | — |
| 184 | Mistral Medium 3 Mistral |
闭源 | 28.78 | — | — | 24.06 | — | 30.06 | — | 45.5 | — | $0.4 | $2 | — |
| 185 | Qwen2.5-72B Alibaba |
开源 | 28.64 | — | — | — | — | — | — | — | — | $0 | $0 | — |
| 186 | Gemma 3 27B |
开源 | 28.55 | 12.06 | 12.41 | 18.59 | — | 24.43 | — | 35.7 | — | $0 | $0 | — |
| 187 | Gemini 1.5 Pro |
闭源 | 28.37 | — | 17.85 | — | — | 28 | — | — | — | $1.25 | $5 | — |
| 188 | Claude 3 Opus Anthropic |
闭源 | 28.27 | — | 14.14 | — | — | 24.65 | — | — | — | $15 | $75 | 200K |
| 189 | Llama 3.1 405B Meta |
开源 | 28.10 | — | — | — | — | — | — | — | — | $0 | $0 | — |
| 190 | Llama 4 Maverick Meta |
开源 | 27.85 | 18.77 | 19.67 | 25.94 | — | 32.12 | — | 50.3 | — | $0 | $0 | — |
| 191 | Claude 3.5 Sonnet Anthropic |
闭源 | 27.74 | — | — | — | — | — | — | — | — | $3 | $15 | 200K |
| 192 | MiniMax M1 80k MiniMax |
闭源 | 27.52 | — | — | — | — | — | — | — | — | — | — | — |
| 193 | Qwen2.5 Coder 32B Instruct Alibaba |
开源 | 27.38 | — | — | — | — | 25.75 | — | — | — | $0 | $0 | — |
| 194 | Mistral Small 4 Mistral |
开源 | 26.98 | 12 | 15.17 | 20.69 | — | 29.16 | — | 57.1 | — | $0.15 | $0.6 | — |
| 195 | Llama 4 Scout Meta |
开源 | 26.95 | 15.31 | 14.98 | 21.81 | — | 27.8 | — | 45.8 | — | $0 | $0 | — |
| 196 | GPT-4o mini OpenAI |
闭源 | 26.62 | — | 11.39 | — | — | 21.72 | — | 34.7 | — | $0.15 | $0.6 | — |
| 197 | Gemma 4 E4B |
开源 | 26.38 | — | 17.38 | 22.84 | 29.12 | 29.11 | — | 51.9 | — | $0 | $0 | — |
| 198 | Granite 4.2 8B IBM |
开源 | 26.13 | 14.69 | 14.66 | 19.98 | — | 27.25 | — | 86.5 | — | $0 | $0 | — |
| 199 | Nemotron 3.5 Lightning 30B A3B NVFP4 NVIDIA |
开源 | 25.47 | 19.17 | 18.49 | — | — | 29.16 | — | 71.4 | — | $0 | $0 | — |
| 200 | LFM2.5-8B-A1B LiquidAI |
开源 | 25.27 | — | — | 22.8 | — | 25.77 | — | 36.5 | 20.5 | $0 | $0 | — |
没有符合条件的模型,换个关键词或筛选试试
当前:综合榜 · 共 200 个模型 · 点击表头可排序 · 按维度排序时缺测评数据的模型排在末尾
分数为第三方测评汇总,仅供参考 · 数据更新于 2026-11-12 01:13 · 来自 BenchLM.ai · 价格单位:美元/百万 tokens
性价比排行 每一块钱能买到多少分 · 价格缺失的模型不参与
性价比 = 综合分 ÷ 平均价((输入价 + 输出价) ÷ 2),单位:分 / 美元
价格 vs 综合分 对数价格轴 · 越靠左上越"又便宜又强"
能力维度曲线对比 默认综合榜前 4 名 · 缺测评数据的维度会出现断点
可下拉更换对比模型
模型能力对比 六个核心维度 · 下拉切换模型即时重绘 · 缺数据维度按 0 绘制
VS
数据更新于 2026-11-12 01:13 · 来自 BenchLM.ai(本站每日自动同步)· 分数为第三方测评汇总仅供参考 · 性价比与图表由浏览器端根据本站最新数据实时计算
