AI Model Intelligence RankingsAI 模型智能排行
60 frontier models, one transparent 100-point Intelligence Score across 11 public benchmarks (reasoning, coding, knowledge, math, agent, human preference). Every score links to its source. Data refreshed 2026-10-20. Click any column to sort.
60 个前沿模型,一套透明的百分制智能评分,覆盖 11 个公开 benchmark(推理/代码/知识/数学/智能体/人类偏好)。每个分数都带来源链接。数据更新于 2026-10-20。点表头可排序。
Find my model帮我选型 Pricing & value价格与性价比 Head-to-head模型对战 Image arena图片生成榜 Video arena视频生成榜 How the score works评分方法 Benchmark explorerBenchmark 百科
Rea = Reasoning推理 Cod = Coding代码 Kno = Knowledge知识 Mat = Math数学 Agt = Agent智能体 Pre = Preference偏好
- Claude Fable 5 — 95.4
- GPT-5.6 Sol — 94.3
- DeepSeek V4 Flash 0731 — 91.1
- GPT-5.6 Terra — 89.7
- Gemini 3.1 Pro Preview — 89.6
- GPT-5.6 Sol Pro — 88.8
- GLM 5.2 — 88.7
- Kimi K3 — 87.9
- DeepSeek V4 Pro 0423 — 87.4
- Claude Opus 4.8 — 87
⚖ Adjust the weights — the ranking recomputes live⚖ 调权重——排名实时重算
Intelligence vs price — the value map智能分 vs 价格——性价比地图
Each dot is a scored model: higher = smarter, further left = cheaper. Top-left is the sweet spot. Color = provider, dashed lines = medians.每个点是一个有评分的模型:越往上越聪明,越往左越便宜,左上角是甜区。颜色=厂商,虚线=中位数。 Click a dot for the model page. 点圆点进模型页。
| # | Model模型 | Score总分 | Rea推理 | Cod代码 | Kno知识 | Mat数学 | Agt智能体 | Pre偏好 | Ctx上下文 | $ in/1M输入$/1M | $ out/1M输出$/1M |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5(max)Anthropic | 1M | $10 | $50 | |||||||
| 2 | GPT-5.6 Sol(max)OpenAI | 1.1M | $4.00 | $20 | |||||||
| 3 | DeepSeek V4 Flash 0731DeepSeek | — | — | 1M | $0.010 | $0.640 | |||||
| 4 | GPT-5.6 Terra(max)OpenAI | 1.1M | $2.00 | $12 | |||||||
| 5 | Gemini 3.1 Pro Preview(high)Google | 1M | $2.00 | $12 | |||||||
| 6 | GPT-5.6 Sol Pro(max)OpenAI | low data数据少 | — | — | — | 1.1M | $4.00 | $20 | |||
| 7 | GLM 5.2(max)Z.ai | 1M | $0.100 | $7.00 | |||||||
| 8 | Kimi K3(always-on常开)Moonshot AI | 1M | $0.300 | $14 | |||||||
| 9 | DeepSeek V4 Pro 0423(max)DeepSeek | 1M | $0.372 | $0.743 | |||||||
| 10 | Claude Opus 4.8(max)Anthropic | 1M | $5.00 | $25 | |||||||
| 11 | Qwen3.8 Max PrimeQwen | 1M | $4.00 | $12 | |||||||
| 12 | Qwen3.7 Max(on/off开/关)Qwen | 1M | $1.48 | $4.42 | |||||||
| 13 | Grok 4.20(high)xAI | 2M | $1.25 | $2.50 | |||||||
| 14 | Claude Opus 5(max)Anthropic | 1M | $5.00 | $25 | |||||||
| 15 | GPT-5.6 Luna(max)OpenAI | — | 1.1M | $0.200 | $1.20 | ||||||
| 16 | Hy3Tencent | low data数据少 | — | — | — | — | 262K | $0.083 | $0.330 | ||
| 17 | Gemini 3.5 Flash(high)Google | 1M | $1.50 | $9.00 | |||||||
| 18 | DeepSeek V4 Flash 0423(max)DeepSeek | 1M | $0.091 | $0.182 | |||||||
| 19 | Qwen3.7 Plus(on/off开/关)Qwen | 1M | $0.320 | $1.28 | |||||||
| 20 | Muse Spark 1.2meta | low data数据少 | — | — | — | 1M | $1.25 | $4.25 | |||
| 21 | GPT-5.5(max)OpenAI | 1.1M | $5.00 | $30 | |||||||
| 22 | Qwen3.7 Flash(on/off开/关)Qwen | — | 1M | $0.030 | $0.130 | ||||||
| 23 | MiniMax M3MiniMax | 1M | $0.300 | $1.20 | |||||||
| 24 | Step 3.7 FlashStepFun | — | 262K | $0.200 | $1.15 | ||||||
| 25 | Claude Sonnet 5(high)Anthropic | 1M | $2.00 | $10 | |||||||
| 26 | Gemini 3.6 Flash(high)Google | — | 1M | $0.750 | $3.75 | ||||||
| 27 | Kimi K2.7 CodeMoonshot AI | 262K | $0.671 | $3.35 | |||||||
| 28 | Grok 4.5(high)xAI | 500K | $2.00 | $6.00 | |||||||
| 29 | Seed-2.0-MiniByteDance Seed | low data数据少 | — | — | — | 262K | $0.100 | $0.400 | |||
| 30 | Nemotron 3 UltraNVIDIA | — | — | 262K | $0.600 | $2.40 | |||||
| 31 | MiniMax M2.7MiniMax | 205K | $0.300 | $1.20 | |||||||
| 32 | MiMo-V2.5-ProXiaomi | low data数据少 | — | — | — | 1.1M | $0.435 | $0.870 | |||
| 33 | Grok 4.3(high)xAI | 1M | $1.25 | $2.50 | |||||||
| 34 | Muse Spark 1.1meta | — | 1M | $1.25 | $4.25 | ||||||
| 35 | GPT-5.6 Luna Pro(max)OpenAI | low data数据少 | — | — | — | 1.1M | $0.200 | $1.20 | |||
| 36 | Kimi K2 Thinking(always-on常开)Moonshot AI | 262K | $0.600 | $2.50 | |||||||
| 37 | DeepSeek V3.2(on/off开/关)DeepSeek | 164K | $0.259 | $0.800 | |||||||
| 38 | GLM 5.1(on/off开/关)Z.ai | 205K | $0.966 | $3.04 | |||||||
| 39 | Mistral Medium 3.5Mistral AI | 262K | $1.50 | $7.50 | |||||||
| 40 | Seed-2.0-LiteByteDance Seed | — | 262K | $0.250 | $2.00 | ||||||
| 41 | gpt-oss-120bOpenAI | 131K | $0.150 | $0.600 | |||||||
| 42 | Gemini 3.5 Flash Lite(high)Google | — | 1M | $0.300 | $2.50 | ||||||
| 43 | Gemini 3.1 Flash Lite(high)Google | — | 1M | $0.250 | $1.50 | ||||||
| 44 | Mercury 2Inception | low data数据少 | — | — | — | 128K | $0.250 | $0.750 | |||
| 45 | Claude Haiku 4.5(high)Anthropic | 200K | $1.00 | $5.00 | |||||||
| 46 | Sonar ProPerplexity | low data数据少 | — | — | — | 200K | $3.00 | $15 | |||
| 47 | Command ACohere | 256K | $2.50 | $10 | |||||||
| 48 | Mistral Small 4Mistral AI | — | 262K | $0.150 | $0.600 | ||||||
| 49 | Mistral LargeMistral AI | — | 128K | $2.00 | $6.00 | ||||||
| 50 | Command R+ (08-2024)Cohere | low data数据少 | — | — | — | 128K | $2.50 | $10 | |||
| 51 | Llama 4 MaverickMeta | 1M | $0.188 | $0.652 | |||||||
| 52 | Nova Pro 1.0Amazon | low data数据少 | — | — | — | 300K | $0.800 | $3.20 | |||
| 53 | Phi 4Microsoft | low data数据少 | — | — | 16K | $0.070 | $0.140 | ||||
| 54 | Llama 4 ScoutMeta | 1.3M | $0.180 | $0.590 | |||||||
| 55 | Nova Premier 1.0Amazon | low data数据少 | — | — | — | 1M | $2.50 | $13 | |||
| — | GPT-5.6 Terra Pro(max)OpenAI | — low data数据少 | — | — | — | 1.1M | $2.00 | $12 | |||
| — | LongCat 2.0Meituan | — low data数据少 | — | — | — | — | 1M | $0.300 | $1.20 | ||
| — | Hunyuan A13B InstructTencent | — low data数据少 | — | — | — | — | 131K | $0.140 | $0.570 | ||
| — | Solar Pro 3Upstage | — low data数据少 | — | — | — | — | 131K | $0.150 | $0.600 | ||
| — | Palmyra X5Writer | — low data数据少 vendor data厂商数据 | — | — | — | — | — | 1M | $0.600 | $6.00 |
55 of 60 models have enough data (≥30% benchmark coverage) for a public score. Prices are API list prices per 1M tokens from OpenRouter. "vendor data" means >40% of available scores are vendor self-reported — treat with care. The Chinese board lists models reachable via CN-direct endpoints, ranked by score.55/60 个模型数据充足(benchmark 覆盖 ≥30%)予以出分。价格为 OpenRouter 每百万 token API 标价。"厂商数据" 表示可用成绩中厂商自报占比超 40%,请谨慎参考。中文榜 = 支持国内直连的模型按分数排序。