排名 ⇕ 模型 ⇕
› 🥇
Claude Fable 5.1 (Max) Anthropic · Proprietary
13.90% ±1.99%
› 🥈
GPT 6 Astra (Max) OpenAI · Proprietary
11.90% ±2.77%
› 🥉
Claude Opus 5 (Max) Anthropic · Proprietary
11.09% ±1.81%
› 4
Claude Opus 5 (High) Anthropic · Proprietary
10.49% ±1.66%
› 5
Claude Fable 5 (High) Anthropic · Proprietary
9.03% ±1.38%
› 6
Claude Opus 4.8 (High) Anthropic · Proprietary
7.75% ±1.40%
› 7
GPT 5.6 Sol (xHigh) OpenAI · Proprietary
7.40% ±1.43%
› 8
Claude Sonnet 5 (High) Anthropic · Proprietary
5.45% ±1.73%
› 9
GPT 5.5 (xHigh) OpenAI · Proprietary
5.18% ±1.07%
› 10
Muse Spark 1.3 (Max) Meta · Proprietary
4.13% ±1.05%
› 11
Qwen3.8 Max 阿里巴巴 · Proprietary
3.57% ±0.93%
› 12
Grok 4.5 SpaceXAI · Proprietary
3.41% ±1.10%
› 13
GPT 5.5 OpenAI · Proprietary
2.62% ±0.93%
› 14
Grok 4.6 (xHigh) SpaceXAI · Proprietary
2.57% ±1.15%
› 15
GPT 5.6 Terra (xHigh) OpenAI · Proprietary
1.58% ±1.19%
› 16
GPT 5.4 (High) OpenAI · Proprietary
1.26% ±0.91%
› 17
GPT 5.6 Luna (xHigh) OpenAI · Proprietary
0.22% ±0.97%
› 18
Claude Sonnet 4.6 Anthropic · Proprietary
1.56% ±1.34%
› 19
Muse Spark 1.2 (xHigh) Meta · Proprietary
1.65% ±1.10%
› 20
Muse Spark 1.1 Meta · Proprietary
3.03% ±0.61%
› 21
Qwen3.7 Max 阿里巴巴 · Proprietary
3.37% ±0.99%
› 22
Gemini 3.6 Flash (High) Google · Proprietary
5.45% ±1.12%
› 23
Qwen3.7 Plus 阿里巴巴 · Proprietary
5.50% ±1.30%
› 24
Gemini 3.1 Pro Preview Google · Proprietary
5.76% ±0.97%
› 25
Gemini 3.5 Flash Lite Google · Proprietary
14.16% ±1.48%

没有找到相关模型