实时模型榜
汇总持续更新的公开评测,保留每个模型的来源、原始成绩与覆盖情况。
实时汇总
5 个独立来源 · 6 张榜单 · 检查于 2026/10/11 05:50 · 内容更新于 2026/10/09 07:25
ECI Epoch Capabilities Index WEB Arena WebDev SWE DeepSWE v1.1 TERM Terminal-Bench 2.0 APEX APEX-Agents ARENA Arena Text
| 排名 | 模型 | 发布时间 | 来源覆盖 | 共识分 |
|---|---|---|---|---|
| 01 | Claude Opus 5.5 Anthropic | 2026-09-22 | | 98.3/100 证据 → |
| 02 | Gemini 4 Argon Google | 2026-09-30 | | 97.0/100 证据 → |
| 03 | Claude Fable 5.1 Anthropic | 2026-09-01 | | 93.1/100 证据 → |
| 04 | Claude Opus 5 Anthropic | 2026-07-24 | | 89.9/100 证据 → |
| 05 | Claude Sonnet 5.5 Anthropic | 2026-09-28 | | 89.7/100 证据 → |
| 06 | GPT-6 Astra OpenAI | 2026-09-03 | | 89.6/100 证据 → |
| 07 | GPT-6.1 Sol OpenAI | 2026-09-29 | | 85.6/100 证据 → |
| 08 | Claude Fable 5 Anthropic | 2026-06-09 | | 84.7/100 证据 → |
| 09 | Gemini 3.8 Flash Google | 2026-09-02 | | 80.0/100 证据 → |
| 10 | GPT-5.3 Codex OpenAI | 2026-02-05 | | 79.8/100 证据 → |
| 11 | Muse Spark 1.3 Meta | 2026-09-02 | | 75.3/100 证据 → |
| 12 | GPT-5.6 Sol OpenAI | 2026-07-09 | | 74.6/100 证据 → |
| 13 | Gemini 3.7 Flash Google | 2026-08-13 | | 73.1/100 证据 → |
| 14 | Mimo V2 6 Pro Xiaomi | 2026-09-21 | | 72.7/100 证据 → |
| 15 | GPT-5.5 OpenAI | 2026-04-23 | | 71.0/100 证据 → |
| 16 | Kimi K3 Moonshot AI | 2026-07-16 | | 70.3/100 证据 → |
| 17 | Claude Opus 4.7 Anthropic | 2026-04-16 | | 68.5/100 证据 → |
| 18 | GPT-5.6 Terra OpenAI | 2026-07-09 | | 67.7/100 证据 → |
| 19 | GLM-5.3 Z.ai | 2026-08-14 | | 66.9/100 证据 → |
| 20 | Qwen 3.8 Max Alibaba | 2026-08-02 | | 66.2/100 证据 → |
| 21 | GPT-6 Sol OpenAI | 2026-09-22 | | 65.8/100 证据 → |
| 22 | Grok 4.6 xAI | 2026-08-12 | | 65.1/100 证据 → |
| 23 | Claude Opus 4.6 Anthropic | 2026-02-05 | | 63.2/100 证据 → |
| 24 | Grok 4.7 xAI | 2026-09-21 | | 58.7/100 证据 → |
| 25 | Claude Opus 4.8 Anthropic | 2026-05-28 | | 57.6/100 证据 → |
| 26 | GPT-5.4 OpenAI | 2026-03-05 | | 56.4/100 证据 → |
| 27 | GPT-6 Luna OpenAI | 2026-09-22 | | 52.4/100 证据 → |
| 28 | Gemini 3 Pro Google | 2025-11-18 | | 51.8/100 证据 → |
| 29 | DeepSeek V4 Pro 0813 DeepSeek | 2026-08-13 | | 51.7/100 证据 → |
| 30 | DeepSeek V4 Flash 0731 DeepSeek | 2026-07-31 | | 50.8/100 证据 → |
| 排名 | 模型 | 发布时间 | 来源覆盖 | 共识分 |
|---|---|---|---|---|
| 01 | Gemini 4 Argon Google | 2026-09-30 | | 100.0/100 证据 → |
| 02 | Claude Opus 5.5 Anthropic | 2026-09-22 | | 99.2/100 证据 → |
| 03 | Claude Fable 5.1 Anthropic | 2026-09-01 | | 92.4/100 证据 → |
| 04 | Claude Fable 5 Anthropic | 2026-06-09 | | 90.7/100 证据 → |
| 05 | GPT-5.5 Pro OpenAI | 2026-04-23 | | 88.1/100 证据 → |
| 06 | Claude Opus 5 Anthropic | 2026-07-24 | | 87.3/100 证据 → |
| 07 | GPT-6.1 Sol OpenAI | 2026-09-29 | | 83.9/100 证据 → |
| 08 | GPT-5.4 Pro OpenAI | 2026-03-05 | | 79.7/100 证据 → |
| 09 | GPT-5.6 Sol OpenAI | 2026-07-09 | | 78.8/100 证据 → |
| 10 | Gemini 3.8 Flash Google | 2026-09-02 | | 78.8/100 证据 → |
| 11 | Muse Spark 1.3 Meta | 2026-09-02 | | 78.8/100 证据 → |
| 12 | Kimi K3 Moonshot AI | 2026-07-16 | | 78.0/100 证据 → |
| 13 | Claude Opus 4.7 Anthropic | 2026-04-16 | | 76.3/100 证据 → |
| 14 | Gemini 3.7 Flash Google | 2026-08-13 | | 75.4/100 证据 → |
| 15 | Claude Sonnet 5.5 Anthropic | 2026-09-28 | | 75.4/100 证据 → |
| 16 | GPT-6 Astra OpenAI | 2026-09-03 | | 74.6/100 证据 → |
| 17 | GPT-5.5 OpenAI | 2026-04-23 | | 73.7/100 证据 → |
| 18 | Claude Opus 4.6 Anthropic | 2026-02-05 | | 73.7/100 证据 → |
| 19 | Claude Opus 4.8 Anthropic | 2026-05-28 | | 71.2/100 证据 → |
| 20 | GPT-5.3 Codex OpenAI | 2026-02-05 | | 71.2/100 证据 → |
| 21 | Qwen 3.8 Max Alibaba | 2026-08-02 | | 66.9/100 证据 → |
| 22 | Muse Spark 1.2 Meta | 2026-08-05 | | 66.1/100 证据 → |
| 23 | GPT-5.4 OpenAI | 2026-03-05 | | 62.7/100 证据 → |
| 24 | GPT-5.6 Luna OpenAI | 2026-07-09 | | 62.7/100 证据 → |
| 25 | Mimo V2 6 Pro Xiaomi | 2026-09-21 | | 62.7/100 证据 → |
| 26 | Gemini 3.1 Pro Google | 2026-02-19 | | 61.0/100 证据 → |
| 27 | Muse Spark 1.1 Meta | 2026-07-09 | | 61.0/100 证据 → |
| 28 | GPT-6 Luna OpenAI | 2026-09-22 | | 61.0/100 证据 → |
| 29 | GLM-5.3 Z.ai | 2026-08-14 | | 58.5/100 证据 → |
| 30 | GPT 5.2 Chat Latest OpenAI | — | | 57.6/100 证据 → |
| 排名 | 模型 | 发布时间 | 来源覆盖 | 共识分 |
|---|---|---|---|---|
| 01 | Claude Opus 5.5 Anthropic | 2026-09-22 | | 100.0/100 证据 → |
| 02 | GPT-6 Astra OpenAI | 2026-09-03 | | 99.2/100 证据 → |
| 03 | Claude Sonnet 5.5 Anthropic | 2026-09-28 | | 96.6/100 证据 → |
| 04 | GPT-6.1 Sol OpenAI | 2026-09-29 | | 94.9/100 证据 → |
| 05 | Claude Fable 5.1 Anthropic | 2026-09-01 | | 93.2/100 证据 → |
| 06 | GPT-6 Sol OpenAI | 2026-09-22 | | 91.5/100 证据 → |
| 07 | Claude Opus 5 Anthropic | 2026-07-24 | | 90.9/100 证据 → |
| 08 | Gemini 4 Argon Google | 2026-09-30 | | 88.1/100 证据 → |
| 09 | Muse Spark 1.3 Meta | 2026-09-02 | | 83.0/100 证据 → |
| 10 | Claude Fable 5 Anthropic | 2026-06-09 | | 81.8/100 证据 → |
| 11 | Grok 4.7 xAI | 2026-09-21 | | 81.4/100 证据 → |
| 12 | GPT-5.6 Sol OpenAI | 2026-07-09 | | 81.3/100 证据 → |
| 13 | Kimi K3 Moonshot AI | 2026-07-16 | | 79.2/100 证据 → |
| 14 | Mimo V2 6 Pro Xiaomi | 2026-09-21 | | 78.0/100 证据 → |
| 15 | Gemini 3.8 Flash Google | 2026-09-02 | | 76.0/100 证据 → |
| 16 | GLM-5.3 Z.ai | 2026-08-14 | | 74.4/100 证据 → |
| 17 | Grok 4.6 xAI | 2026-08-12 | | 72.1/100 证据 → |
| 18 | DeepSeek V4.1 Flash DeepSeek | 2026-09-09 | | 71.2/100 证据 → |
| 19 | Qwen 3.8 27B Alibaba | 2026-08-14 | | 67.8/100 证据 → |
| 20 | Qwen 3.8 Max Alibaba | 2026-08-02 | | 64.4/100 证据 → |
| 21 | GPT-6 Luna OpenAI | 2026-09-22 | | 62.7/100 证据 → |
| 22 | DeepSeek V4 Pro 0813 DeepSeek | 2026-08-13 | | 61.0/100 证据 → |
| 23 | GLM-5.3-Flash Z.ai | 2026-08-20 | | 60.7/100 证据 → |
| 24 | GPT-5.6 Terra OpenAI | 2026-07-09 | | 60.3/100 证据 → |
| 25 | Gemini 3.7 Flash Google | 2026-08-13 | | 60.2/100 证据 → |
| 26 | DeepSeek V4 Flash 0731 DeepSeek | 2026-07-31 | | 59.3/100 证据 → |
| 27 | Step 5 StepFun | 2026-09-18 | | 57.6/100 证据 → |
| 28 | Claude Opus 4.7 Anthropic | 2026-04-16 | | 54.2/100 证据 → |
| 29 | Claude Opus 4.6 Anthropic | 2026-02-05 | | 50.9/100 证据 → |
| 30 | GPT-5.6 Luna OpenAI | 2026-07-09 | | 50.6/100 证据 → |
| 排名 | 模型 | 发布时间 | 来源覆盖 | 共识分 |
|---|---|---|---|---|
| 01 | Gemini 4 Argon Google | 2026-09-30 | | 100.0/100 证据 → |
| 02 | Claude Sonnet 5.5 Anthropic | 2026-09-28 | | 97.9/100 证据 → |
| 03 | Claude Opus 5.5 Anthropic | 2026-09-22 | | 95.8/100 证据 → |
| 04 | Claude Fable 5.1 Anthropic | 2026-09-01 | | 93.8/100 证据 → |
| 05 | Gemini 3.7 Flash Google | 2026-08-13 | | 91.7/100 证据 → |
| 06 | Claude Opus 5 Anthropic | 2026-07-24 | | 89.6/100 证据 → |
| 07 | GPT-5.3 Codex OpenAI | 2026-02-05 | | 88.4/100 证据 → |
| 08 | Grok 4.6 xAI | 2026-08-12 | | 87.5/100 证据 → |
| 09 | Gemini 3 Pro Google | 2025-11-18 | | 86.0/100 证据 → |
| 10 | GPT-6 Astra OpenAI | 2026-09-03 | | 85.4/100 证据 → |
| 11 | GPT-5.2-Codex OpenAI | 2025-12-18 | | 83.7/100 证据 → |
| 12 | Gemini 3.8 Flash Google | 2026-09-02 | | 83.3/100 证据 → |
| 13 | GPT-5.5 OpenAI | 2026-04-23 | | 82.3/100 证据 → |
| 14 | GPT-5.2 OpenAI | 2025-12-11 | | 81.4/100 证据 → |
| 15 | Claude Fable 5 Anthropic | 2026-06-09 | | 81.3/100 证据 → |
| 16 | Qwen 3.8 Max Alibaba | 2026-08-02 | | 79.2/100 证据 → |
| 17 | Gemini 3 Flash Google | 2025-12-17 | | 79.1/100 证据 → |
| 18 | GPT-6.1 Sol OpenAI | 2026-09-29 | | 77.1/100 证据 → |
| 19 | Claude Opus 4.5 Anthropic | 2025-11-24 | | 76.7/100 证据 → |
| 20 | GPT-5.4 OpenAI | 2026-03-05 | | 75.9/100 证据 → |
| 21 | Mimo V2 6 Pro Xiaomi | 2026-09-21 | | 75.0/100 证据 → |
| 22 | GPT-5.1-Codex-Mini OpenAI | 2025-11-12 | | 74.4/100 证据 → |
| 23 | GPT-5.6 Terra OpenAI | 2026-07-09 | | 72.9/100 证据 → |
| 24 | GPT-5.1-Codex OpenAI | 2025-11-19 | | 72.1/100 证据 → |
| 25 | Muse Spark 1.3 Meta | 2026-09-02 | | 70.8/100 证据 → |
| 26 | Claude Opus 4.7 Anthropic | 2026-04-16 | | 70.5/100 证据 → |
| 27 | Grok 4.20 xAI | 2026-02-17 | | 69.8/100 证据 → |
| 28 | GLM-5.3 Z.ai | 2026-08-14 | | 68.8/100 证据 → |
| 29 | Grok 4.5 xAI | 2026-07-08 | | 66.7/100 证据 → |
| 30 | GLM 5 Z.ai | 2026-02-11 | | 65.1/100 证据 → |