| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Opus 5.5 (Max)
Anthropic · Proprietary
|
19.83% ±2.85% |
|
›
🥈
|
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
13.86% ±2.30% |
|
›
🥉
|
Claude Sonnet 5.5 (Max)
Anthropic · Proprietary
|
13.66% ±3.56% |
|
›
4
|
GPT-6.1 Sol (Max)
OpenAI · Proprietary
|
13.58% ±1.92% |
|
›
5
|
GPT-6 Astra (Max)
OpenAI · Proprietary
|
13.17% ±2.54% |
|
›
6
|
Gemini 4 Argon (High)
Google · Proprietary
|
10.88% ±1.06% |
|
›
7
|
Muse Wonder Full (Max)
Meta · Proprietary
|
9.82% ±1.60% |
|
›
8
|
Kimi K3.1 Pro (Max)
月之暗面 · Proprietary · Preliminary
|
9.65% ±3.75% |
|
›
9
|
GPT-6 Sol (Max)
OpenAI · Proprietary
|
8.62% ±2.03% |
|
›
10
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
8.10% ±1.70% |
|
›
11
|
Claude Opus 5 (Max)
Anthropic · Proprietary
|
7.84% ±1.87% |
|
›
12
|
GPT-5.6 Sol (xHigh)
OpenAI · Proprietary
|
6.64% ±1.60% |
|
›
13
|
DeepSeek-V4.1-Flash-20261017 (Max)
DeepSeek · MIT
|
5.58% ±0.99% |
|
›
14
|
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
5.39% ±2.04% |
|
›
15
|
Muse Wonder (Max)
Meta · Proprietary
|
3.87% ±1.74% |
|
›
16
|
MiMo-V2.6-Pro
小米 · MIT
|
3.44% ±0.95% |
|
›
17
|
Muse Spark 1.3 (Max)
Meta · Proprietary
|
3.34% ±0.99% |
|
›
18
|
GPT-6 Luna (Max)
OpenAI · Proprietary
|
3.22% ±0.50% |
|
›
19
|
GLM-5.2 (Max)
智谱 ZAI · MIT
|
2.84% ±0.98% |
|
›
20
|
DeepSeek-V4.1-Flash-20260910 (Max)
DeepSeek · MIT
|
2.54% ±0.41% |
|
›
21
|
Grok 4.7 (xHigh)
SpaceXAI · Proprietary
|
2.53% ±1.80% |
|
›
22
|
MiMo-V2.6-Flash
小米 · MIT
|
2.49% ±1.54% |
|
›
23
|
Claude Haiku 5.5 (High)
Anthropic · Proprietary
|
2.13% ±1.17% |
|
›
24
|
Hy4 preview
腾讯 · Apache 2.0
|
2.11% ±0.75% |
|
›
25
|
Gemini 3.8 Flash (High)
Google · Proprietary
|
1.97% ±1.26% |
|
›
26
|
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
1.83% ±0.86% |
|
›
27
|
GLM-5.3 (Max)
智谱 ZAI · MIT
|
1.70% ±0.99% |
|
›
28
|
Qwen3.8-Max
阿里巴巴 · Proprietary
|
1.05% ±0.72% |
|
›
29
|
GPT-5.6 Terra (xHigh)
OpenAI · Proprietary
|
0.75% ±1.62% |
|
›
30
|
DeepSeek-V4-Pro (High, 20260813)
DeepSeek · MIT
|
0.59% ±1.99% |
|
›
31
|
GPT-6 Luna (Medium)
OpenAI · Proprietary
|
0.46% ±1.07% |
|
›
32
|
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
0.42% ±1.33% |
|
›
33
|
Step 5 Preview
阶跃星辰 · Proprietary
|
0.51% ±1.75% |
|
›
34
|
MiniMax-M3.1-Flash
MiniMax · MiniMax Community License · Preliminary
|
1.70% ±2.17% |
|
›
35
|
GLM-5.3-Flash
智谱 ZAI · MIT
|
1.82% ±0.78% |
|
›
36
|
Gemini 3.7 Flash (High)
Google · Proprietary
|
2.62% ±1.14% |
|
›
37
|
Beam 1.0 501B A23B
Reflection · Apache 2.0
|
2.86% ±2.79% |
|
›
38
|
Qwen3.8-Flash-Next
阿里巴巴 · Qwen-community-1.0
|
3.00% ±0.83% |
|
›
39
|
Qwen3.8-27B
阿里巴巴 · Apache 2.0
|
3.59% ±0.93% |
|
›
40
|
GPT-6 Luna (Low)
OpenAI · Proprietary
|
4.62% ±1.17% |
|
›
41
|
Mistral Large 4
Mistral · Proprietary
|
4.82% ±2.61% |
|
›
42
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
5.12% ±1.60% |
|
›
43
|
Hy3
腾讯 · Apache 2.0
|
5.82% ±1.78% |
|
›
44
|
Qwen3.7-Max
阿里巴巴 · Proprietary
|
6.74% ±1.34% |
|
›
45
|
Muse Spark 1.1
Meta · Proprietary
|
7.71% ±0.76% |
|
›
46
|
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
7.97% ±0.96% |
|
›
47
|
Qwen3.7-Plus
阿里巴巴 · Proprietary
|
8.20% ±2.23% |
|
›
48
|
MiMo-V2.5-Pro
小米 · MIT
|
8.75% ±1.16% |
|
›
49
|
MiniMax-M3
MiniMax · MiniMax Community License
|
9.97% ±1.45% |
|
›
50
|
Mistral Medium 3.5
Mistral · Modified MIT
|
12.80% ±2.06% |
|
›
51
|
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
NVIDIA · OpenMDW-1.1
|
14.56% ±2.28% |
|
›
52
|
Inkling
Thinky · Apache 2.0
|
15.81% ±1.75% |
|
›
53
|
Inkling-Small
Thinky · Apache 2.0
|
15.94% ±2.15% |
|
›
54
|
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
16.86% ±5.13% |
|
›
55
|
Solar Pro 4
Upstage · Proprietary
|
21.42% ±2.57% |
没有找到相关模型