Finance Agent v2.1 - Market Analysis
Professional Work · 2026-10-19
Partial-credit score on the Market Analysis category of Finance Agent v2.1.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 4 Argon | 70.7 |
| Gemini 3.8 Flash | 70.5 |
| GLM-5.3 Flash | 67.9 |
| Muse Wonder | 67.7 |
| Muse Wonder Full | 67.4 |
| DeepSeek V4.1 Flash | 67.1 |
| Hy4 Preview | 66.9 |
| Mistral Large 4 Preview | 66.6 |
| Step 5 Preview | 65.2 |
| GPT-6 Astra | 64.2 |
| Grok 4.7 | 64.0 |
| DeepSeek V4 Pro 0813 | 63.0 |
| MiniMax M3 | 62.2 |
| Claude Haiku 5.5 | 61.4 |
| MiMo-V2.6-Pro | 61.0 |
| GLM-5.3 | 61.0 |
| GPT-6.1 Sol | 61.0 |
| DeepSeek V4.1 Flash 1017 | 60.7 |
| Mercury 3 | 60.7 |
| Muse Spark Open | 56.6 |
| MiniMax M3.1 Flash | 55.7 |
| MiMo-V2.6-Flash | 55.0 |
| GPT-6 Luna | 52.4 |
| Kimi K3 | 52.1 |
| Beam 1.0 501B A23B | 50.9 |
| Inkling | 49.8 |
| Inkling-Small | 43.6 |