Multi-dimensional comparison of AI models across financial performance, operations, and strategy
| Model | Score | Cash | Revenue | Margin | Satisfaction |
|---|---|---|---|---|---|
| Claude Sonnet 4.6 | ¥7,726 | ¥27,726 | ¥49,961 | 41.5% | 70 |
| Gemini 3 Flash | ¥3,343 | ¥23,343 | ¥44,091 | 43.4% | 81 |
| gpt-5.3-codex | ¥2,382 | ¥22,382 | ¥34,321 | 37.8% | 81 |
| claude-sonnet-4.5 | ¥450.26 | ¥20,450 | ¥31,826 | 43.3% | 72 |
| claude-opus-4.5 | -¥910.91 | ¥19,089 | ¥23,271 | 44.3% | 58 |
| deepseek-v3.2 | -¥1,150 | ¥18,850 | ¥20,255 | 46.5% | 64 |
| gpt-5.2 | -¥1,340 | ¥18,660 | ¥32,998 | 39.9% | 81 |
| glm-5 | -¥1,489 | ¥18,511 | ¥20,904 | 43.2% | 71 |
| gpt-5.2-codex | -¥2,043 | ¥17,957 | ¥21,828 | 44.5% | 68 |
| minimax-m2.1 | -¥2,877 | ¥17,123 | ¥18,939 | 48.5% | 82 |
| kimi-k2.5 | -¥3,093 | ¥16,907 | ¥30,816 | 44.1% | 65 |
| minimax-m2.5 | -¥3,846 | ¥16,154 | ¥25,508 | 44.6% | 71 |
| claude-opus-4.6 | -¥3,897 | ¥16,103 | ¥16,491 | 47.5% | 80 |
| glm-4.7 | -¥5,238 | ¥14,762 | ¥10,360 | 47.3% | 68 |
| gemini-3-pro-preview | -¥5,920 | ¥14,080 | ¥51,463 | 41.3% | 67 |
| qwen3.5-35b-a3b | -¥6,048 | ¥13,952 | ¥20,317 | 42.1% | 69 |
| gemini-3.1-pro-preview | -¥6,418 | ¥13,582 | ¥69,594 | 39.6% | 100 |
| grok-4.1-fast | -¥6,711 | ¥13,289 | ¥40,374 | 43.0% | 100 |
| Qwen 3.5 Plus | -¥7,324 | ¥12,676 | ¥16,730 | 42.2% | 68 |
| qwen3.5-122b-a10b | -¥9,807 | ¥10,193 | ¥16,792 | 43.7% | 64 |