Name: 智能体模型厂商排行榜（2026-06-11）- 最佳 Agent 模型对比 - 厂商聚合排名
Creator: LM Arena
License: https://creativecommons.org/licenses/by/4.0/
Keywords: AI 智能体模型排行榜,智能体 AI 排行榜,最佳 Agent 模型对比,AI 模型排行,智能体评测,净提升

排名Rank ⇕	厂商Lab ⇕
› 🥇	AnthropicAnthropic Claude Fable 5 (High) · Proprietary	12.94% ±2.10%

综合排名Overall Rank — 名次区间Rank Spread 1 ↔ 2 确认成功Confirmed Success ▲17.55%±3.21% 赞扬/抱怨Praise vs Complaint ▲28.86%±7.97% 可控性Steerability ▲5.39%±4.14% Bash 恢复Bash Recovery ▲10.87%±1.76% 工具幻觉Tool Hallucination ▼2.05%±0.26% 会话数Sessions 11,675
› 🥈	OpenAIOpenAI GPT 5.5 (xHigh) · Proprietary	10.56% ±3.05%

综合排名Overall Rank — 名次区间Rank Spread 1 ↔ 9 确认成功Confirmed Success ▲5.36%±5.15% 赞扬/抱怨Praise vs Complaint ▲29.39%±11.53% 可控性Steerability ▲1.86%±5.95% Bash 恢复Bash Recovery ▲14.11%±2.30% 工具幻觉Tool Hallucination ▼2.05%±0.26% 会话数Sessions 4,486
› 🥉	智谱 ZAIZ.ai GLM 5.1 · MIT · SiliconFlow	2.44% ±1.23%

综合排名Overall Rank — 名次区间Rank Spread 10 ↔ 13 确认成功Confirmed Success ▲4.74%±2.52% 赞扬/抱怨Praise vs Complaint ▲0.63%±4.28% 可控性Steerability ▲0.28%±2.51% Bash 恢复Bash Recovery ▲5.06%±1.46% 工具幻觉Tool Hallucination ▼2.05%±0.26% 会话数Sessions 26,218
› 4	DeepSeekDeepSeek DeepSeek V4 Pro · MIT · SiliconFlow	0.05% ±1.21%

综合排名Overall Rank — 名次区间Rank Spread 12 ↔ 17 确认成功Confirmed Success ▲2.55%±2.50% 赞扬/抱怨Praise vs Complaint ▲1.58%±4.24% 可控性Steerability ▲3.30%±2.48% Bash 恢复Bash Recovery ▲1.99%±1.13% 工具幻觉Tool Hallucination ▼0.57%±0.39% 会话数Sessions 26,485
› 5	GoogleGoogle Gemini 3.5 Flash · Proprietary	0.21% ±1.08%

综合排名Overall Rank — 名次区间Rank Spread 13 ↔ 17 确认成功Confirmed Success ▲2.76%±2.42% 赞扬/抱怨Praise vs Complaint ▲2.15%±3.59% 可控性Steerability ▲0.98%±2.06% Bash 恢复Bash Recovery ▲2.84%±1.34% 工具幻觉Tool Hallucination ▼1.99%±0.27% 会话数Sessions 24,166
› 6	月之暗面Moonshot Kimi K2.6 · Modified MIT · Fireworks	0.45% ±1.10%

综合排名Overall Rank — 名次区间Rank Spread 13 ↔ 17 确认成功Confirmed Success ▲0.24%±2.39% 赞扬/抱怨Praise vs Complaint ▲4.00%±3.73% 可控性Steerability ▲2.78%±2.30% Bash 恢复Bash Recovery ▲2.25%±1.39% 工具幻觉Tool Hallucination ▼2.05%±0.26% 会话数Sessions 27,636
› 7	阿里巴巴Alibaba Qwen 3.6 Plus · Proprietary · Fireworks	4.12% ±1.25%

综合排名Overall Rank — 名次区间Rank Spread 18 ↔ 19 确认成功Confirmed Success ▲1.82%±2.56% 赞扬/抱怨Praise vs Complaint ▲7.04%±4.18% 可控性Steerability ▲8.97%±2.69% Bash 恢复Bash Recovery ▲1.65%±1.80% 工具幻觉Tool Hallucination ▼1.12%±0.57% 会话数Sessions 25,834
› 8	xAIxAI Grok Build 0.1 · Proprietary	5.87% ±1.14%

综合排名Overall Rank — 名次区间Rank Spread 18 ↔ 20 确认成功Confirmed Success ▲6.63%±2.65% 赞扬/抱怨Praise vs Complaint ▲12.34%±3.59% 可控性Steerability ▲8.82%±2.38% Bash 恢复Bash Recovery ▲3.30%±1.56% 工具幻觉Tool Hallucination ▼4.85%±0.72% 会话数Sessions 21,227
› 9	MiniMaxMiniMax Minimax M2.7 · Modified MIT · Fireworks	7.86% ±1.10%

综合排名Overall Rank — 名次区间Rank Spread 19 ↔ 22 确认成功Confirmed Success ▲10.66%±2.67% 赞扬/抱怨Praise vs Complaint ▲18.85%±3.29% 可控性Steerability ▲9.10%±2.24% Bash 恢复Bash Recovery ▲2.68%±1.85% 工具幻觉Tool Hallucination ▼2.01%±0.27% 会话数Sessions 26,478

没有找到相关模型No matching models found

AI 智能体模型排行榜Agent Models Leaderboard 🏆 综合榜单