| 排名Rank | 综合排名 / 区间Overall Rank / Range | 厂商Lab | 确认成功Confirmed Success | 赞扬/抱怨Praise vs Complaint | 可控性Steerability | Bash 恢复Bash Recovery | 工具幻觉Tool Hallucination | 会话数Sessions | |
|---|---|---|---|---|---|---|---|---|---|
| 🥇 | 1 1 - 3 |
Anthropic
Top Model: Claude Opus 5 (High)
|
13.74%±1.80% | 14.96%±3.73% | 21.82%±6.81% | 16.00%±3.26% | 15.13%±0.84% | 0.80%±0.14% | 21.7K |
| 🥈 | 4 2 - 8 |
OpenAI
Top Model: GPT 5.6 Sol (xHigh)
|
9.49%±1.51% | 7.57%±3.20% | 21.62%±5.62% | 8.73%±2.88% | 8.68%±1.02% | 0.86%±0.14% | 28.8K |
| 🥉 | 6 3 - 8 |
月之暗面
Top Model: Kimi K3 (Max)
|
8.71%±0.66% | 16.90%±1.35% | 15.85%±2.31% | 2.13%±1.29% | 7.79%±0.54% | 0.86%±0.14% | 95.3K |
| 4 | 10 7 - 18 |
智谱 ZAI
Top Model: GLM 5.2 (Max)
|
6.23%±0.77% | 8.65%±1.66% | 11.26%±2.71% | 5.41%±1.41% | 4.97%±0.78% | 0.86%±0.14% | 66.1K |
| 5 | 12 7 - 19 |
SpaceXAI
Top Model: Grok 4.5
|
6.17%±1.15% | 6.32%±2.55% | 5.73%±4.09% | 7.30%±2.24% | 10.61%±1.14% | 0.86%±0.14% | 34.3K |
| 6 | 16 7 - 19 |
DeepSeek
Top Model: DeepSeek V4 Pro (High) (0813)
|
5.91%±1.04% | 13.14%±2.13% | 5.47%±3.51% | 1.06%±2.31% | 9.03%±0.84% | 0.86%±0.14% | 26.5K |
| 7 | 18 8 - 22 |
阿里巴巴
Top Model: Qwen3.8 Max
|
5.24%±1.13% | 8.38%±2.50% | 6.47%±3.89% | 4.56%±2.26% | 6.91%±1.01% | 0.11%±0.26% | 18.6K |
| 8 | 31 23 - 35 |
Meta
Top Model: Muse Spark 1.2 (xHigh)
|
0.85%±1.13% | 6.27%±2.82% | 6.45%±3.37% | 5.70%±2.43% | 9.29%±1.40% | 0.85%±0.14% | 18.4K |
| 9 | 33 24 - 33 |
Google
Top Model: Gemini 3.7 Flash (High)
|
0.84%±0.91% | 9.80%±2.13% | 1.60%±2.93% | 5.38%±1.90% | 0.61%±1.07% | 0.79%±0.15% | 24.4K |
| 10 | 38 28 - 45 |
腾讯
Top Model: Hy3
|
1.51%±1.34% | 3.87%±2.96% | 1.46%±4.38% | 0.62%±2.62% | 0.30%±2.33% | 1.32%±0.54% | 23.8K |
| 11 | 44 37 - 45 |
MiniMax
Top Model: Minimax M3
|
3.57%±0.92% | 7.76%±2.48% | 10.33%±2.71% | 5.33%±1.86% | 5.16%±0.87% | 0.43%±0.22% | 35.8K |
| 12 | 45 37 - 45 |
小米
Top Model: Mimo V2.5 Pro
|
3.57%±0.96% | 5.06%±2.44% | 8.72%±2.85% | 2.63%±1.82% | 1.17%±1.73% | 0.27%±0.33% | 36.5K |
| 13 | 47 37 - 48 |
Thinky
Top Model: Inkling Small
|
4.53%±1.83% | 16.84%±5.04% | 14.91%±5.42% | 2.72%±4.39% | 11.66%±1.31% | 0.17%±0.36% | 10.4K |
| 14 | 48 44 - 48 |
Mistral
Top Model: Mistral Medium 3.5
|
6.45%±1.64% | 12.71%±4.06% | 12.28%±4.62% | 0.76%±3.72% | 4.38%±2.45% | 2.10%±1.13% | 8.0K |
| 15 | 50 45 - 54 |
Upstage
Top Model: Solar Pro 4
|
9.34%±3.39% | 8.27%±7.12% | 13.42%±9.20% | 1.14%±6.90% | 23.12%±8.77% | 0.74%±1.72% | 5.8K |
| 16 | 56 48 - 54 |
NVIDIA
Top Model: Nemotron 3 Ultra
|
13.73%±2.59% | 15.49%±5.44% | 14.74%±6.79% | 9.06%±5.22% | 29.64%±7.30% | 0.27%±0.29% | 12.3K |
没有找到匹配的模型,换个关键词试试?No matching models found. Try a different keyword?
Anthropic
OpenAI
月之暗面
智谱 ZAI
SpaceXAI
DeepSeek
阿里巴巴
Meta
Google
腾讯
MiniMax
小米
Mistral
NVIDIA