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 2026/09/16 01:05 · 内容更新于 2026/09/15 15:35
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 Fable 5.1 Anthropic | 2026-09-01 | | 98.0/100 证据 → |
| 02 | GPT-6 Astra OpenAI | 2026-09-03 | | 95.3/100 证据 → |
| 03 | Claude Opus 5 Anthropic | 2026-07-24 | | 93.4/100 证据 → |
| 04 | Claude Fable 5 Anthropic | 2026-06-09 | | 92.9/100 证据 → |
| 05 | GPT-5.6 Sol OpenAI | 2026-07-09 | | 87.1/100 证据 → |
| 06 | Gemini 3.8 Flash Google | 2026-09-02 | | 84.3/100 证据 → |
| 07 | Kimi K3 Moonshot AI | 2026-07-16 | | 81.5/100 证据 → |
| 08 | Claude Opus 4.7 Anthropic | 2026-04-16 | | 80.5/100 证据 → |
| 09 | GPT-5.5 OpenAI | 2026-04-23 | | 78.2/100 证据 → |
| 10 | GPT-5.3 Codex OpenAI | 2026-02-05 | | 76.7/100 证据 → |
| 11 | Claude Opus 4.6 Anthropic | 2026-02-05 | | 75.5/100 证据 → |
| 12 | Claude Opus 4.8 Anthropic | 2026-05-28 | | 74.1/100 证据 → |
| 13 | Gemini 3.7 Flash Google | 2026-08-13 | | 73.2/100 证据 → |
| 14 | GPT-5.2-Codex OpenAI | 2025-12-18 | | 72.6/100 证据 → |
| 15 | GPT-5.6 Terra OpenAI | 2026-07-09 | | 72.4/100 证据 → |
| 16 | GLM-5.3 Z.ai | 2026-08-14 | | 71.7/100 证据 → |
| 17 | DeepSeek V4 Pro 0813 DeepSeek | 2026-08-13 | | 71.2/100 证据 → |
| 18 | Grok 4.6 xAI | 2026-08-12 | | 70.5/100 证据 → |
| 19 | Qwen 3.8 Max Alibaba | 2026-08-02 | | 67.8/100 证据 → |
| 20 | GPT-5.4 OpenAI | 2026-03-05 | | 65.9/100 证据 → |
| 21 | DeepSeek V4 Flash 0731 DeepSeek | 2026-07-31 | | 63.6/100 证据 → |
| 22 | GPT-5.1-Codex OpenAI | 2025-11-19 | | 62.0/100 证据 → |
| 23 | Muse Spark 1.1 Meta | 2026-07-09 | | 61.8/100 证据 → |
| 24 | Muse Spark 1.2 Meta | 2026-08-05 | | 61.4/100 证据 → |
| 25 | Gemini 3 Pro Google | 2025-11-18 | | 61.1/100 证据 → |
| 26 | GPT-5.2 OpenAI | 2025-12-11 | | 60.8/100 证据 → |
| 27 | Gemini 3 Flash Google | 2025-12-17 | | 55.7/100 证据 → |
| 28 | GPT-5.6 Luna OpenAI | 2026-07-09 | | 55.5/100 证据 → |
| 29 | Gemini 3.1 Pro Google | 2026-02-19 | | 55.3/100 证据 → |
| 30 | Claude Sonnet 5 Anthropic | 2026-06-30 | | 54.7/100 证据 → |
| 排名 | 模型 | 发布时间 | 来源覆盖 | 共识分 |
|---|---|---|---|---|
| 01 | Claude Fable 5 Anthropic | 2026-06-09 | | 98.3/100 证据 → |
| 02 | Claude Fable 5.1 Anthropic | 2026-09-01 | | 95.8/100 证据 → |
| 03 | GPT-5.5 Pro OpenAI | 2026-04-23 | | 93.2/100 证据 → |
| 04 | Claude Opus 5 Anthropic | 2026-07-24 | | 91.5/100 证据 → |
| 05 | Muse Spark 1 3 Meta | — | | 91.5/100 证据 → |
| 06 | GPT-5.4 Pro OpenAI | 2026-03-05 | | 86.4/100 证据 → |
| 07 | GPT-5.6 Sol OpenAI | 2026-07-09 | | 83.9/100 证据 → |
| 08 | Claude Opus 4.7 Anthropic | 2026-04-16 | | 83.9/100 证据 → |
| 09 | Gemini 3.7 Flash Google | 2026-08-13 | | 83.1/100 证据 → |
| 10 | GPT-6 Astra OpenAI | 2026-09-03 | | 83.0/100 证据 → |
| 11 | Gemini 3.8 Flash Google | 2026-09-02 | | 82.2/100 证据 → |
| 12 | GPT-5.5 OpenAI | 2026-04-23 | | 80.5/100 证据 → |
| 13 | Kimi K3 Moonshot AI | 2026-07-16 | | 80.5/100 证据 → |
| 14 | Muse Spark 1.2 Meta | 2026-08-05 | | 80.5/100 证据 → |
| 15 | Claude Opus 4.6 Anthropic | 2026-02-05 | | 79.7/100 证据 → |
| 16 | Claude Opus 4.8 Anthropic | 2026-05-28 | | 78.0/100 证据 → |
| 17 | GPT-5.3 Codex OpenAI | 2026-02-05 | | 76.3/100 证据 → |
| 18 | Qwen 3.8 Max Alibaba | 2026-08-02 | | 73.7/100 证据 → |
| 19 | GPT-5.4 OpenAI | 2026-03-05 | | 71.2/100 证据 → |
| 20 | Muse Spark 1.1 Meta | 2026-07-09 | | 69.5/100 证据 → |
| 21 | Gemini 3.1 Pro Google | 2026-02-19 | | 68.6/100 证据 → |
| 22 | GLM-5.3 Z.ai | 2026-08-14 | | 67.0/100 证据 → |
| 23 | DeepSeek V4 Pro 0813 DeepSeek | 2026-08-13 | | 64.4/100 证据 → |
| 24 | GPT-5.6 Terra OpenAI | 2026-07-09 | | 63.6/100 证据 → |
| 25 | GPT-5.2 Pro OpenAI | 2025-12-11 | | 62.7/100 证据 → |
| 26 | Gemini 3 Pro Google | 2025-11-18 | | 61.0/100 证据 → |
| 27 | Muse Spark Meta | 2026-04-08 | | 61.0/100 证据 → |
| 28 | GPT 5.2 Chat Latest OpenAI | — | | 61.0/100 证据 → |
| 29 | Gemini 3.5 Flash Google | 2026-05-19 | | 59.3/100 证据 → |
| 30 | Gemini 3.6 Flash Google | 2026-07-21 | | 58.5/100 证据 → |
| 排名 | 模型 | 发布时间 | 来源覆盖 | 共识分 |
|---|---|---|---|---|
| 01 | GPT-6 Astra OpenAI | 2026-09-03 | | 100.0/100 证据 → |
| 02 | Claude Fable 5.1 Anthropic | 2026-09-01 | | 98.3/100 证据 → |
| 03 | Claude Opus 5 Anthropic | 2026-07-24 | | 94.3/100 证据 → |
| 04 | GPT-5.6 Sol OpenAI | 2026-07-09 | | 88.1/100 证据 → |
| 05 | Claude Fable 5 Anthropic | 2026-06-09 | | 86.9/100 证据 → |
| 06 | Gemini 3.8 Flash Google | 2026-09-02 | | 85.3/100 证据 → |
| 07 | Kimi K3 Moonshot AI | 2026-07-16 | | 83.5/100 证据 → |
| 08 | Qwen3.8 27b Alibaba | 2026-08-14 | | 83.0/100 证据 → |
| 09 | GLM-5.3 Z.ai | 2026-08-14 | | 80.4/100 证据 → |
| 10 | Grok 4.6 xAI | 2026-08-12 | | 79.8/100 证据 → |
| 11 | DeepSeek V4 Pro 0813 DeepSeek | 2026-08-13 | | 78.0/100 证据 → |
| 12 | DeepSeek V4 Flash 0731 DeepSeek | 2026-07-31 | | 76.3/100 证据 → |
| 13 | Claude Opus 4.7 Anthropic | 2026-04-16 | | 72.9/100 证据 → |
| 14 | GLM-5.3-Flash Z.ai | 2026-08-20 | | 69.2/100 证据 → |
| 15 | GPT-5.6 Terra OpenAI | 2026-07-09 | | 68.8/100 证据 → |
| 16 | Qwen 3.8 Max Alibaba | 2026-08-02 | | 68.6/100 证据 → |
| 17 | Claude Opus 4.6 Anthropic | 2026-02-05 | | 67.8/100 证据 → |
| 18 | Gemini 3.7 Flash Google | 2026-08-13 | | 67.8/100 证据 → |
| 19 | GPT-5.6 Luna OpenAI | 2026-07-09 | | 60.0/100 证据 → |
| 20 | Claude Opus 4.8 Anthropic | 2026-05-28 | | 59.6/100 证据 → |
| 21 | Qwen3.7 Alibaba | 2026-05-19 | | 54.2/100 证据 → |
| 22 | GPT-5.5 OpenAI | 2026-04-23 | | 53.7/100 证据 → |
| 23 | Muse Spark Meta | 2026-04-08 | | 52.5/100 证据 → |
| 24 | GLM-5.1 Z.ai | 2026-04-07 | | 50.9/100 证据 → |
| 25 | Grok 4.5 xAI | 2026-07-08 | | 50.7/100 证据 → |
| 26 | Muse Spark 1.2 Meta | 2026-08-05 | | 50.5/100 证据 → |
| 27 | Claude Sonnet 5 Anthropic | 2026-06-30 | | 49.4/100 证据 → |
| 28 | Kimi K2.6 Moonshot AI | 2026-04-20 | | 49.1/100 证据 → |
| 29 | GLM-5.2 Z.ai | 2026-06-16 | | 48.7/100 证据 → |
| 30 | Muse Spark 1.1 Meta | 2026-07-09 | | 47.0/100 证据 → |
| 排名 | 模型 | 发布时间 | 来源覆盖 | 共识分 |
|---|---|---|---|---|
| 01 | Claude Fable 5.1 Anthropic | 2026-09-01 | | 100.0/100 证据 → |
| 02 | GPT-6 Astra OpenAI | 2026-09-03 | | 98.1/100 证据 → |
| 03 | Claude Fable 5 Anthropic | 2026-06-09 | | 96.2/100 证据 → |
| 04 | Claude Opus 5 Anthropic | 2026-07-24 | | 94.2/100 证据 → |
| 05 | Claude Opus 4.8 Anthropic | 2026-05-28 | | 92.3/100 证据 → |
| 06 | GPT-5.5 OpenAI | 2026-04-23 | | 91.3/100 证据 → |
| 07 | Muse Spark 1.1 Meta | 2026-07-09 | | 90.4/100 证据 → |
| 08 | GPT-5.4 OpenAI | 2026-03-05 | | 89.2/100 证据 → |
| 09 | Grok 4.6 xAI | 2026-08-12 | | 88.5/100 证据 → |
| 10 | GPT-5.6 Sol OpenAI | 2026-07-09 | | 86.5/100 证据 → |
| 11 | Kimi K3 Moonshot AI | 2026-07-16 | | 84.6/100 证据 → |
| 12 | Gemini 3.1 Pro Google | 2026-02-19 | | 83.3/100 证据 → |
| 13 | Claude Opus 4.7 Anthropic | 2026-04-16 | | 83.0/100 证据 → |
| 14 | GPT-5.2 OpenAI | 2025-12-11 | | 79.2/100 证据 → |
| 15 | Claude Opus 4.6 Anthropic | 2026-02-05 | | 79.0/100 证据 → |
| 16 | GLM-5.2 Z.ai | 2026-06-16 | | 78.8/100 证据 → |
| 17 | GPT-5.3 Codex OpenAI | 2026-02-05 | | 76.9/100 证据 → |
| 18 | Grok 4.5 xAI | 2026-07-08 | | 75.0/100 证据 → |
| 19 | Gemini 3 Pro Google | 2025-11-18 | | 74.8/100 证据 → |
| 20 | GPT-5.1-Codex-Mini OpenAI | 2025-11-12 | | 74.4/100 证据 → |
| 21 | GPT-5.2-Codex OpenAI | 2025-12-18 | | 72.6/100 证据 → |
| 22 | Grok 4.20 xAI | 2026-02-17 | | 69.8/100 证据 → |
| 23 | Claude Sonnet 5 Anthropic | 2026-06-30 | | 69.2/100 证据 → |
| 24 | Gemini 3 Flash Google | 2025-12-17 | | 67.4/100 证据 → |
| 25 | Claude Opus 4.5 Anthropic | 2025-11-24 | | 63.4/100 证据 → |
| 26 | GPT-5.1-Codex OpenAI | 2025-11-19 | | 62.0/100 证据 → |
| 27 | Claude Sonnet 4.6 Anthropic | 2026-02-17 | | 60.6/100 证据 → |
| 28 | Kimi K2.7 Code Moonshot AI | 2026-06-12 | | 59.6/100 证据 → |
| 29 | Claude Sonnet 4.5 Anthropic | 2025-09-29 | | 58.1/100 证据 → |
| 30 | GPT-5.4 Mini OpenAI | 2026-03-17 | | 57.7/100 证据 → |