跳转到内容

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

评分方法与来源说明

色块表示该模型被哪些榜单收录

排名 模型 发布时间 来源覆盖 共识分
01 Claude Opus 5.5 Anthropic 2026-09-22
4/6
98.3/100 证据 →
02 Gemini 4 Argon Google 2026-09-30
3/6
97.0/100 证据 →
03 Claude Fable 5.1 Anthropic 2026-09-01
4/6
93.1/100 证据 →
04 Claude Opus 5 Anthropic 2026-07-24
5/6
89.9/100 证据 →
05 Claude Sonnet 5.5 Anthropic 2026-09-28
4/6
89.7/100 证据 →
06 GPT-6 Astra OpenAI 2026-09-03
5/6
89.6/100 证据 →
07 GPT-6.1 Sol OpenAI 2026-09-29
4/6
85.6/100 证据 →
08 Claude Fable 5 Anthropic 2026-06-09
5/6
84.7/100 证据 →
09 Gemini 3.8 Flash Google 2026-09-02
5/6
80.0/100 证据 →
10 GPT-5.3 Codex OpenAI 2026-02-05
2/6
79.8/100 证据 →
11 Muse Spark 1.3 Meta 2026-09-02
4/6
75.3/100 证据 →
12 GPT-5.6 Sol OpenAI 2026-07-09
5/6
74.6/100 证据 →
13 Gemini 3.7 Flash Google 2026-08-13
5/6
73.1/100 证据 →
14 Mimo V2 6 Pro Xiaomi 2026-09-21
3/6
72.7/100 证据 →
15 GPT-5.5 OpenAI 2026-04-23
6/6
71.0/100 证据 →
16 Kimi K3 Moonshot AI 2026-07-16
5/6
70.3/100 证据 →
17 Claude Opus 4.7 Anthropic 2026-04-16
5/6
68.5/100 证据 →
18 GPT-5.6 Terra OpenAI 2026-07-09
5/6
67.7/100 证据 →
19 GLM-5.3 Z.ai 2026-08-14
5/6
66.9/100 证据 →
20 Qwen 3.8 Max Alibaba 2026-08-02
5/6
66.2/100 证据 →
21 GPT-6 Sol OpenAI 2026-09-22
4/6
65.8/100 证据 →
22 Grok 4.6 xAI 2026-08-12
5/6
65.1/100 证据 →
23 Claude Opus 4.6 Anthropic 2026-02-05
5/6
63.2/100 证据 →
24 Grok 4.7 xAI 2026-09-21
3/6
58.7/100 证据 →
25 Claude Opus 4.8 Anthropic 2026-05-28
5/6
57.6/100 证据 →
26 GPT-5.4 OpenAI 2026-03-05
6/6
56.4/100 证据 →
27 GPT-6 Luna OpenAI 2026-09-22
3/6
52.4/100 证据 →
28 Gemini 3 Pro Google 2025-11-18
4/6
51.8/100 证据 →
29 DeepSeek V4 Pro 0813 DeepSeek 2026-08-13
3/6
51.7/100 证据 →
30 DeepSeek V4 Flash 0731 DeepSeek 2026-07-31
2/6
50.8/100 证据 →