Name: 智能体 AI 排行榜 - 最佳 Agent 模型对比 (2026-08-06 历史榜单)
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 ⇕	模型Model ⇕
› 🥇	Claude Opus 5 (High) Anthropic · Proprietary	11.99% ±1.37%

综合排名Overall Rank — 名次区间Rank Spread 1 ↔ 6 确认成功Confirmed Success ▲16.04%±2.79% 赞扬/抱怨Praise vs Complaint ▲19.46%±5.19% 可控性Steerability ▲10.29%±2.51% Bash 恢复Bash Recovery ▲13.07%±0.78% 工具幻觉Tool Hallucination ▼1.07%±0.16% 会话数Sessions 19,487
› 🥈	Claude Fable 5 (High) Anthropic · Proprietary	11.66% ±2.39%

综合排名Overall Rank — 名次区间Rank Spread 1 ↔ 9 确认成功Confirmed Success ▲11.47%±4.46% 赞扬/抱怨Praise vs Complaint ▲22.56%±8.25% 可控性Steerability ▲10.01%±4.93% Bash 恢复Bash Recovery ▲13.10%±3.52% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 24,249
› 🥉	Claude Opus 5 (Max) Anthropic · Proprietary	11.19% ±1.62%

综合排名Overall Rank — 名次区间Rank Spread 1 ↔ 8 确认成功Confirmed Success ▲16.36%±3.11% 赞扬/抱怨Praise vs Complaint ▲19.07%±6.03% 可控性Steerability ▲5.80%±3.10% Bash 恢复Bash Recovery ▲13.62%±0.88% 工具幻觉Tool Hallucination ▼1.12%±0.16% 会话数Sessions 15,227
› 4	GPT 5.6 Sol (xHigh) OpenAI · Proprietary	10.28% ±1.72%

综合排名Overall Rank — 名次区间Rank Spread 1 ↔ 10 确认成功Confirmed Success ▲9.06%±3.48% 赞扬/抱怨Praise vs Complaint ▲22.70%±6.42% 可控性Steerability ▲8.42%±3.50% Bash 恢复Bash Recovery ▲10.07%±1.23% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 17,800
› 5	Kimi K3 (Max) 月之暗面 · Kimi K3 license	10.08% ±1.07%

综合排名Overall Rank — 名次区间Rank Spread 1 ↔ 9 确认成功Confirmed Success ▲14.97%±2.09% 赞扬/抱怨Praise vs Complaint ▲19.68%±3.85% 可控性Steerability ▲7.45%±1.97% Bash 恢复Bash Recovery ▲7.13%±0.89% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 26,156
› 6	Claude Opus 4.8 (Thinking) Anthropic · Proprietary	9.35% ±1.70%

综合排名Overall Rank — 名次区间Rank Spread 1 ↔ 12 确认成功Confirmed Success ▲8.81%±2.90% 赞扬/抱怨Praise vs Complaint ▲21.46%±5.38% 可控性Steerability ▲8.50%±3.08% Bash 恢复Bash Recovery ▲9.17%±2.57% 工具幻觉Tool Hallucination ▼1.19%±2.88% 会话数Sessions 34,962
› 7	GPT 5.5 (xHigh) OpenAI · Proprietary	8.45% ±0.99%

综合排名Overall Rank — 名次区间Rank Spread 3 ↔ 13 确认成功Confirmed Success ▲5.24%±2.08% 赞扬/抱怨Praise vs Complaint ▲13.56%±3.55% 可控性Steerability ▲8.19%±1.80% Bash 恢复Bash Recovery ▲14.13%±1.19% 工具幻觉Tool Hallucination ▼1.15%±0.16% 会话数Sessions 46,499
› 8	Claude Opus 4.7 (Thinking) Anthropic · Proprietary	8.33% ±1.32%

综合排名Overall Rank — 名次区间Rank Spread 2 ↔ 13 确认成功Confirmed Success ▲6.65%±2.76% 赞扬/抱怨Praise vs Complaint ▲11.87%±4.59% 可控性Steerability ▲8.61%±2.72% Bash 恢复Bash Recovery ▲13.47%±1.10% 工具幻觉Tool Hallucination ▼1.04%±0.19% 会话数Sessions 35,949
› 9	Claude Sonnet 5 (High) Anthropic · Proprietary	7.46% ±2.15%

综合排名Overall Rank — 名次区间Rank Spread 2 ↔ 17 确认成功Confirmed Success ▲5.56%±4.29% 赞扬/抱怨Praise vs Complaint ▲14.80%±7.65% 可控性Steerability ▲5.14%±4.55% Bash 恢复Bash Recovery ▲10.79%±1.56% 工具幻觉Tool Hallucination ▼1.01%±0.17% 会话数Sessions 25,493
› 10	Claude Opus 4.7 Anthropic · Proprietary	7.32% ±1.36%

综合排名Overall Rank — 名次区间Rank Spread 5 ↔ 17 确认成功Confirmed Success ▲5.55%±2.85% 赞扬/抱怨Praise vs Complaint ▲10.72%±4.45% 可控性Steerability ▲9.54%±2.70% Bash 恢复Bash Recovery ▲9.69%±2.12% 工具幻觉Tool Hallucination ▼1.10%±0.16% 会话数Sessions 36,507
› 11	GPT 5.5 (High) OpenAI · Proprietary	7.27% ±0.93%

综合排名Overall Rank — 名次区间Rank Spread 6 ↔ 15 确认成功Confirmed Success ▲3.56%±1.95% 赞扬/抱怨Praise vs Complaint ▲10.25%±3.27% 可控性Steerability ▲9.09%±1.66% Bash 恢复Bash Recovery ▲12.32%±0.99% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 71,703
› 12	GLM 5.2 (Max) 智谱 ZAI · MIT	6.75% ±0.90%

综合排名Overall Rank — 名次区间Rank Spread 7 ↔ 17 确认成功Confirmed Success ▲9.21%±1.83% 赞扬/抱怨Praise vs Complaint ▲12.39%±3.21% 可控性Steerability ▲5.62%±1.59% Bash 恢复Bash Recovery ▲5.37%±1.12% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 50,093
› 13	Claude Opus 4.6 Anthropic · Proprietary	6.39% ±1.33%

综合排名Overall Rank — 名次区间Rank Spread 6 ↔ 18 确认成功Confirmed Success ▲4.23%±2.83% 赞扬/抱怨Praise vs Complaint ▲8.25%±4.33% 可控性Steerability ▲7.36%±2.59% Bash 恢复Bash Recovery ▲10.95%±1.90% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 35,700
› 14	GPT 5.5 OpenAI · Proprietary	5.77% ±0.87%

综合排名Overall Rank — 名次区间Rank Spread 9 ↔ 18 确认成功Confirmed Success ▲2.91%±1.89% 赞扬/抱怨Praise vs Complaint ▲7.36%±3.04% 可控性Steerability ▲6.18%±1.59% Bash 恢复Bash Recovery ▲11.22%±0.96% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 72,848
› 15	Grok 4.5 SpaceXAI · Proprietary	5.57% ±1.27%

综合排名Overall Rank — 名次区间Rank Spread 9 ↔ 20 确认成功Confirmed Success ▲5.00%±2.82% 赞扬/抱怨Praise vs Complaint ▲5.29%±4.52% 可控性Steerability ▲4.82%±2.39% Bash 恢复Bash Recovery ▲11.57%±1.09% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 27,653
› 16	GPT 5.4 (High) OpenAI · Proprietary	5.28% ±0.90%

综合排名Overall Rank — 名次区间Rank Spread 10 ↔ 18 确认成功Confirmed Success ▲4.87%±1.94% 赞扬/抱怨Praise vs Complaint ▲4.04%±3.15% 可控性Steerability ▲6.61%±1.68% Bash 恢复Bash Recovery ▲9.71%±0.94% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 72,066
› 17	GPT 5.6 Luna (xHigh) OpenAI · Proprietary	4.42% ±1.79%

综合排名Overall Rank — 名次区间Rank Spread 10 ↔ 22 确认成功Confirmed Success ▲0.64%±3.96% 赞扬/抱怨Praise vs Complaint ▲7.59%±6.32% 可控性Steerability ▲1.73%±3.68% Bash 恢复Bash Recovery ▲11.01%±1.39% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 8,431
› 18	GPT 5.6 Terra (xHigh) OpenAI · Proprietary	3.06% ±1.30%

综合排名Overall Rank — 名次区间Rank Spread 16 ↔ 22 确认成功Confirmed Success ▲2.64%±3.18% 赞扬/抱怨Praise vs Complaint ▲2.68%±4.37% 可控性Steerability ▲5.04%±2.52% Bash 恢复Bash Recovery ▲9.05%±1.20% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 12,427
› 19	Claude Opus 4.8 Anthropic · Proprietary	3.04% ±2.18%

综合排名Overall Rank — 名次区间Rank Spread 13 ↔ 25 确认成功Confirmed Success ▲8.78%±2.94% 赞扬/抱怨Praise vs Complaint ▲13.52%±5.18% 可控性Steerability ▲8.10%±3.02% Bash 恢复Bash Recovery ▲9.80%±2.39% 工具幻觉Tool Hallucination ▼25.02%±7.64% 会话数Sessions 33,005
› 20	Claude Sonnet 4.6 Anthropic · Proprietary	3.00% ±1.33%

综合排名Overall Rank — 名次区间Rank Spread 16 ↔ 23 确认成功Confirmed Success ▲0.13%±2.91% 赞扬/抱怨Praise vs Complaint ▲1.22%±4.02% 可控性Steerability ▲2.12%±2.56% Bash 恢复Bash Recovery ▲10.46%±2.58% 工具幻觉Tool Hallucination ▼1.05%±0.21% 会话数Sessions 36,461
› 21	Deepseek V4 Flash (High) (20260731) DeepSeek · MIT	2.84% ±1.10%

综合排名Overall Rank — 名次区间Rank Spread 17 ↔ 22 确认成功Confirmed Success ▲8.53%±2.54% 赞扬/抱怨Praise vs Complaint ▲0.46%±3.64% 可控性Steerability ▲0.43%±2.19% Bash 恢复Bash Recovery ▲3.64%±1.01% 工具幻觉Tool Hallucination ▼1.15%±0.16% 会话数Sessions 18,925
› 22	Muse Spark 1.1 Meta · Proprietary	0.91% ±0.62%

综合排名Overall Rank — 名次区间Rank Spread 21 ↔ 28 确认成功Confirmed Success ▲6.14%±1.43% 赞扬/抱怨Praise vs Complaint ▲4.86%±1.85% 可控性Steerability ▲3.71%±1.18% Bash 恢复Bash Recovery ▲5.89%±1.28% 工具幻觉Tool Hallucination ▼1.11%±0.16% 会话数Sessions 62,721
› 23	Kimi K2.7 Code 月之暗面 · Modified MIT	0.69% ±1.94%

综合排名Overall Rank — 名次区间Rank Spread 17 ↔ 31 确认成功Confirmed Success ▲4.12%±4.08% 赞扬/抱怨Praise vs Complaint ▲2.36%±6.68% 可控性Steerability ▲1.92%±4.37% Bash 恢复Bash Recovery ▲2.26%±2.64% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 10,853
› 24	GLM 5.1 智谱 ZAI · MIT	0.35% ±0.77%

综合排名Overall Rank — 名次区间Rank Spread 21 ↔ 30 确认成功Confirmed Success ▲1.06%±1.72% 赞扬/抱怨Praise vs Complaint ▲0.72%±2.50% 可控性Steerability ▲0.76%±1.40% Bash 恢复Bash Recovery ▲0.61%±1.36% 工具幻觉Tool Hallucination ▼0.15%±0.31% 会话数Sessions 69,327
› 25	Qwen3.7 Max 阿里巴巴 · Proprietary	0.16% ±0.88%

综合排名Overall Rank — 名次区间Rank Spread 22 ↔ 31 确认成功Confirmed Success ▲0.24%±2.11% 赞扬/抱怨Praise vs Complaint ▲5.07%±2.72% 可控性Steerability ▲0.21%±1.55% Bash 恢复Bash Recovery ▲4.20%±1.49% 工具幻觉Tool Hallucination ▼0.51%±0.26% 会话数Sessions 27,375
› 26	DeepSeek V4 Pro DeepSeek · MIT	0.33% ±0.86%

综合排名Overall Rank — 名次区间Rank Spread 22 ↔ 31 确认成功Confirmed Success ▲2.74%±2.16% 赞扬/抱怨Praise vs Complaint ▲3.35%±2.78% 可控性Steerability ▲0.30%±1.54% Bash 恢复Bash Recovery ▲3.82%±0.92% 工具幻觉Tool Hallucination ▼0.33%±0.27% 会话数Sessions 28,084
› 27	Kimi K2.6 月之暗面 · Modified MIT	0.48% ±2.16%

综合排名Overall Rank — 名次区间Rank Spread 20 ↔ 35 确认成功Confirmed Success ▲2.28%±4.11% 赞扬/抱怨Praise vs Complaint ▲2.12%±6.80% 可控性Steerability ▲1.66%±4.49% Bash 恢复Bash Recovery ▲6.27%±4.39% 工具幻觉Tool Hallucination ▼1.16%±0.16% 会话数Sessions 10,970
› 28	Gemini 3.1 Pro Preview Google · Proprietary	0.54% ±0.71%

综合排名Overall Rank — 名次区间Rank Spread 23 ↔ 31 确认成功Confirmed Success ▲1.71%±1.57% 赞扬/抱怨Praise vs Complaint ▲2.91%±2.23% 可控性Steerability ▲2.78%±1.23% Bash 恢复Bash Recovery ▲11.13%±1.34% 工具幻觉Tool Hallucination ▼1.01%±0.20% 会话数Sessions 79,360
› 29	Gemini 3.5 Flash (High) Google · Proprietary	0.73% ±0.59%

综合排名Overall Rank — 名次区间Rank Spread 23 ↔ 31 确认成功Confirmed Success ▲0.24%±1.40% 赞扬/抱怨Praise vs Complaint ▲1.09%±1.83% 可控性Steerability ▲0.98%±1.05% Bash 恢复Bash Recovery ▲1.98%±0.95% 工具幻觉Tool Hallucination ▼0.16%±0.20% 会话数Sessions 90,015
› 30	Hy3 腾讯 · Apache 2.0	1.12% ±1.42%

综合排名Overall Rank — 名次区间Rank Spread 22 ↔ 35 确认成功Confirmed Success ▲2.20%±3.04% 赞扬/抱怨Praise vs Complaint ▲3.70%±4.91% 可控性Steerability ▲9.01%±2.60% Bash 恢复Bash Recovery ▲2.82%±1.82% 工具幻觉Tool Hallucination ▼0.89%±0.63% 会话数Sessions 14,807
› 31	Qwen3.7 Plus 阿里巴巴 · Proprietary	1.87% ±1.31%

综合排名Overall Rank — 名次区间Rank Spread 24 ↔ 36 确认成功Confirmed Success ▲0.07%±3.33% 赞扬/抱怨Praise vs Complaint ▲10.87%±3.94% 可控性Steerability ▲3.78%±2.73% Bash 恢复Bash Recovery ▲5.29%±1.96% 工具幻觉Tool Hallucination ▼0.07%±0.40% 会话数Sessions 15,926
› 32	Mimo V2.5 Pro 小米 · MIT	2.42% ±0.92%

综合排名Overall Rank — 名次区间Rank Spread 29 ↔ 36 确认成功Confirmed Success ▲3.88%±2.24% 赞扬/抱怨Praise vs Complaint ▲7.27%±2.82% 可控性Steerability ▲2.19%±1.68% Bash 恢复Bash Recovery ▲1.30%±1.45% 工具幻觉Tool Hallucination ▼0.08%±0.35% 会话数Sessions 27,785
› 33	Minimax M3 MiniMax · MiniMax Community License	2.47% ±0.85%

综合排名Overall Rank — 名次区间Rank Spread 29 ↔ 36 确认成功Confirmed Success ▲5.15%±2.21% 赞扬/抱怨Praise vs Complaint ▲9.10%±2.65% 可控性Steerability ▲4.19%±1.64% Bash 恢复Bash Recovery ▲5.48%±0.82% 工具幻觉Tool Hallucination ▼0.59%±0.33% 会话数Sessions 27,674
› 34	DeepSeek V4 Flash DeepSeek · MIT	2.70% ±0.88%

综合排名Overall Rank — 名次区间Rank Spread 29 ↔ 36 确认成功Confirmed Success ▲3.12%±2.37% 赞扬/抱怨Praise vs Complaint ▲10.05%±2.68% 可控性Steerability ▲1.90%±1.67% Bash 恢复Bash Recovery ▲2.82%±0.97% 工具幻觉Tool Hallucination ▼1.25%±0.39% 会话数Sessions 23,569
› 35	gemini-3.6-flash Google · Proprietary	2.73% ±1.38%

综合排名Overall Rank — 名次区间Rank Spread 29 ↔ 36 确认成功Confirmed Success ▲1.01%±3.37% 赞扬/抱怨Praise vs Complaint ▲5.99%±4.30% 可控性Steerability ▲4.56%±2.80% Bash 恢复Bash Recovery ▲3.19%±1.82% 工具幻觉Tool Hallucination ▼1.11%±0.18% 会话数Sessions 9,009
› 36	Gemini 3.5 Flash (Medium) Google · Proprietary	4.29% ±1.49%

综合排名Overall Rank — 名次区间Rank Spread 31 ↔ 38 确认成功Confirmed Success ▲9.94%±3.70% 赞扬/抱怨Praise vs Complaint ▲5.61%±4.44% 可控性Steerability ▲4.99%±2.87% Bash 恢复Bash Recovery ▲1.19%±2.47% 工具幻觉Tool Hallucination ▼0.30%±0.82% 会话数Sessions 11,957
› 37	Inkling Thinky · Apache 2.0	6.60% ±0.89%

综合排名Overall Rank — 名次区间Rank Spread 36 ↔ 39 确认成功Confirmed Success ▲11.06%±2.48% 赞扬/抱怨Praise vs Complaint ▲16.01%±2.60% 可控性Steerability ▲12.57%±1.77% Bash 恢复Bash Recovery ▲6.15%±1.08% 工具幻觉Tool Hallucination ▼0.48%±0.24% 会话数Sessions 32,583
› 38	Mistral Medium 3.5 Mistral · Modified MIT	6.82% ±2.16%

综合排名Overall Rank — 名次区间Rank Spread 36 ↔ 42 确认成功Confirmed Success ▲10.43%±5.02% 赞扬/抱怨Praise vs Complaint ▲8.71%±6.47% 可控性Steerability ▲11.31%±4.31% Bash 恢复Bash Recovery ▲0.13%±2.86% 工具幻觉Tool Hallucination ▼3.53%±2.85% 会话数Sessions 4,844
› 39	Grok 4.3 (High) SpaceXAI · Proprietary	8.30% ±0.83%

综合排名Overall Rank — 名次区间Rank Spread 37 ↔ 42 确认成功Confirmed Success ▲9.31%±1.74% 赞扬/抱怨Praise vs Complaint ▲13.95%±1.93% 可控性Steerability ▲6.51%±1.26% Bash 恢复Bash Recovery ▲12.72%±2.73% 工具幻觉Tool Hallucination ▼1.00%±0.16% 会话数Sessions 60,015
› 40	Grok Build 0.1 SpaceXAI · Proprietary	8.82% ±0.87%

综合排名Overall Rank — 名次区间Rank Spread 38 ↔ 42 确认成功Confirmed Success ▲5.31%±1.80% 赞扬/抱怨Praise vs Complaint ▲11.12%±2.27% 可控性Steerability ▲9.95%±1.54% Bash 恢复Bash Recovery ▲18.59%±2.55% 工具幻觉Tool Hallucination ▼0.85%±0.16% 会话数Sessions 71,454
› 41	Gemini 3 Flash Google · Proprietary	8.92% ±0.76%

综合排名Overall Rank — 名次区间Rank Spread 38 ↔ 42 确认成功Confirmed Success ▲8.51%±1.64% 赞扬/抱怨Praise vs Complaint ▲11.36%±1.85% 可控性Steerability ▲4.37%±1.20% Bash 恢复Bash Recovery ▲20.36%±2.21% 工具幻觉Tool Hallucination ▼0.01%±0.77% 会话数Sessions 80,624
› 42	gemini-3.5-flash-lite Google · Proprietary	10.37% ±1.43%

综合排名Overall Rank — 名次区间Rank Spread 38 ↔ 44 确认成功Confirmed Success ▲14.10%±3.56% 赞扬/抱怨Praise vs Complaint ▲13.30%±3.78% 可控性Steerability ▲10.72%±2.74% Bash 恢复Bash Recovery ▲13.31%±3.09% 工具幻觉Tool Hallucination ▼0.45%±0.62% 会话数Sessions 9,015
› 43	Minimax M2.7 MiniMax · Modified MIT	11.59% ±1.10%

综合排名Overall Rank — 名次区间Rank Spread 42 ↔ 44 确认成功Confirmed Success ▲13.21%±2.52% 赞扬/抱怨Praise vs Complaint ▲15.89%±2.95% 可控性Steerability ▲13.41%±2.01% Bash 恢复Bash Recovery ▲16.44%±2.91% 工具幻觉Tool Hallucination ▼1.01%±0.19% 会话数Sessions 27,865
› 44	Nemotron 3 Ultra NVIDIA · OpenMDW-1.1	13.75% ±2.33%

综合排名Overall Rank — 名次区间Rank Spread 42 ↔ 46 确认成功Confirmed Success ▲16.20%±5.23% 赞扬/抱怨Praise vs Complaint ▲14.76%±6.61% 可控性Steerability ▲19.08%±4.76% Bash 恢复Bash Recovery ▲19.00%±5.52% 工具幻觉Tool Hallucination ▼0.30%±0.41% 会话数Sessions 11,618
› 45	Grok 4.3 SpaceXAI · Proprietary	14.86% ±1.14%

综合排名Overall Rank — 名次区间Rank Spread 44 ↔ 46 确认成功Confirmed Success ▲11.77%±1.67% 赞扬/抱怨Praise vs Complaint ▲16.19%±1.82% 可控性Steerability ▲6.44%±1.21% Bash 恢复Bash Recovery ▲40.98%±4.91% 工具幻觉Tool Hallucination ▼1.06%±0.16% 会话数Sessions 79,964
› 46	Gemma 4 31B Google · Apache 2.0	17.60% ±2.38%

综合排名Overall Rank — 名次区间Rank Spread 44 ↔ 46 确认成功Confirmed Success ▲0.27%±1.93% 赞扬/抱怨Praise vs Complaint ▲2.90%±2.87% 可控性Steerability ▲9.16%±1.83% Bash 恢复Bash Recovery ▲44.31%±8.51% 工具幻觉Tool Hallucination ▼31.37%±7.31% 会话数Sessions 56,459

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