Agent Leaderboard
Agent Leaderboard
50 个模型
| 模型 | ||||||||
|---|---|---|---|---|---|---|---|---|
1 | Claude Opus 5.5 (Max)Anthropic · 商业版 | ▲ 20.77%±2.38% | ▲ 22.08%±3.38% | ▲ 45.32%±9.27% | ▲ 17.60%±1.99% | ▲ 15.50%±0.82% | ▲ 0.57%±0.13% | 12,057 |
2 | Claude Sonnet 5.5 (Max)Anthropic · 商业版 | ▲ 13.99%±3.04% | ▲ 21.70%±4.75% | ▲ 23.20%±11.70% | ▲ 10.82%±3.58% | ▲ 13.32%±0.84% | ▲ 0.65%±0.13% | 8,097 |
3 | GPT-6 Astra (Max)OpenAI · 商业版 | ▲ 13.96%±2.08% | ▲ 13.25%±3.59% | ▲ 29.76%±7.58% | ▲ 14.46%±2.13% | — | ▲ 0.71%±0.08% | 14,567 |
4 | Claude Fable 5.1 (Max)Anthropic · 商业版 | ▲ 13.94%±1.93% | ▲ 13.86%±3.44% | ▲ 27.66%±7.13% | ▲ 15.33%±2.14% | ▲ 10.80%±1.11% | ▲ 0.61%±0.14% | 17,062 |
5 | GPT-6.1 Sol (Max)OpenAI · 商业版 | ▲ 13.64%±1.63% | ▲ 13.73%±2.75% | ▲ 31.26%±5.97% | ▲ 13.70%±1.62% | — | ▲ 0.75%±0.06% | 16,092 |
6 | Gemini 4 Argon (High)Google · 商业版 | ▲ 11.75%±0.91% | ▲ 13.51%±1.61% | ▲ 26.62%±3.19% | ▲ 14.40%±0.99% | ▼ 1.78%±2.37% | ▲ 0.35%±0.14% | 45,840 |
7 | GPT-6 Sol (Max)OpenAI · 商业版 | ▲ 8.57%±1.71% | ▲ 6.90%±3.42% | ▲ 14.10%±5.86% | ▲ 11.07%±1.84% | — | ▲ 0.64%±0.07% | 10,305 |
8 | Claude Opus 5 (Max)Anthropic · 商业版 | ▲ 8.22%±1.63% | ▲ 11.58%±2.98% | ▲ 12.36%±5.48% | ▲ 6.69%±2.11% | ▲ 11.85%±1.06% | ▲ 0.70%±0.08% | 24,440 |
9 | Claude Fable 5 (High)Anthropic · 商业版 | ▲ 7.75%±1.40% | ▲ 3.43%±2.75% | ▲ 15.28%±4.48% | ▲ 9.60%±1.92% | ▲ 12.87%±1.65% | ▲ 0.64%±0.17% | 43,567 |
10 | GPT-5.6 Sol (xHigh)OpenAI · 商业版 | ▲ 6.06%±1.34% | ▲ 1.86%±2.80% | ▲ 10.37%±4.19% | ▲ 8.41%±1.83% | — | ▲ 0.62%±0.10% | 37,542 |
11 | Claude Sonnet 5 (High)Anthropic · 商业版 | ▲ 3.75%±1.70% | ▼ 1.05%±3.54% | ▲ 3.81%±5.24% | ▲ 5.96%±2.33% | ▲ 15.57%±1.05% | ▲ 0.45%±0.15% | 33,991 |
12 | Muse Wonder (Max)Meta · 商业版 | ▲ 3.31%±1.57% | ▲ 7.67%±3.26% | ▲ 1.07%±4.72% | ▲ 3.73%±2.14% | ▲ 7.37%±5.00% | ▼ 0.84%±2.18% | 11,134 |
13 | MiMo-V2.6-ProXiaomi · 开源 | ▲ 3.30%±0.81% | ▲ 6.87%±1.66% | ▲ 4.12%±2.56% | ▲ 2.11%±1.16% | — | ▼ 0.06%±0.23% | 43,983 |
14 | Gemini 3.8 Flash (High)Google · 商业版 | ▲ 3.17%±1.08% | ▲ 2.91%±2.26% | ▲ 4.17%±3.25% | ▲ 1.16%±1.59% | ▲ 11.23%±0.52% | ▲ 0.56%±0.11% | 39,719 |
15 | Muse Spark 1.3 (Max)Meta · 商业版 | ▲ 3.05%±0.83% | ▲ 4.26%±1.71% | ▲ 2.87%±2.64% | ▲ 4.81%±1.10% | ▲ 2.42%±0.92% | ▲ 0.66%±0.08% | 78,017 |
16 | Grok 4.7 (xHigh)SpaceXAI · 商业版 | ▲ 3.02%±1.57% | ▲ 6.04%±3.24% | ▲ 3.55%±4.92% | ▼ 1.50%±2.32% | ▲ 8.98%±0.81% | ▲ 0.68%±0.07% | 16,639 |
17 | GPT-6 Luna (Max)OpenAI · 商业版 | ▲ 2.79%±0.42% | ▲ 0.46%±0.92% | ▲ 0.50%±1.35% | ▲ 5.65%±0.54% | — | ▲ 0.61%±0.07% | 194,437 |
18 | DeepSeek-V4.1-Flash-20260910 (Max)DeepSeek · 开源 | ▲ 2.25%±0.34% | ▲ 5.79%±0.72% | ▲ 2.94%±1.09% | ▲ 0.99%±0.49% | — | ▲ 0.55%±0.07% | 259,479 |
19 | MiMo-V2.6-FlashXiaomi · 开源 | ▲ 2.10%±1.33% | ▲ 6.17%±2.67% | ▲ 2.56%±4.29% | ▲ 4.65%±1.68% | — | ▼ 2.99%±0.44% | 22,895 |
20 | Hy4 previewTencent · 开源 | ▲ 2.02%±0.64% | ▲ 5.10%±1.35% | ▲ 3.43%±2.03% | ▲ 1.56%±0.85% | ▼ 2.00%±0.59% | ▲ 0.09%±0.18% | 93,764 |
Agent Leaderboard
Oct 23, 2026 · 2,466,325 场对话 · 50 个模型