Finance Agent v2 - General Quantitative Analysis
Professional Work · 2026-05-19
The General Quantitative Analysis split of Finance Agent v2. This child benchmark separates a source-reported subtask or subtrack from the parent aggregate so scores at different grains do not share one benchmark_slug.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 3.7 Flash | 81.8 |
| Gemini 3.6 Flash | 81.8 |
| Gemini 4 Argon | 81.5 |
| Gemini 3.8 Flash | 80.9 |
| Muse Spark Open | 80.6 |
| Muse Wonder Full | 80.1 |
| MiMo-V2.6-Pro | 79.8 |
| Claude Fable 5.1 | 79.7 |
| DeepSeek V4.1 Flash 1017 | 79.2 |
| GPT-6 Astra | 78.8 |
| Muse Spark 1.2 | 78.4 |
| Muse Spark 1.3 | 78.0 |
| Muse Wonder | 77.6 |
| Gemini 3.5 Flash | 77.6 |
| Muse Spark 1.1 | 76.8 |
| GLM-5.3 Flash | 76.4 |
| Qwen3.8 Max (0902) | 76.1 |
| Mistral Large 4 Preview | 75.7 |
| GPT-5.6 Sol | 75.6 |
| Hy4 Preview | 75.5 |
| GPT-5.6 Luna | 75.2 |
| Ember-1 | 75.1 |
| Kimi K3 | 74.8 |
| GPT-6.1 Sol | 74.5 |
| Claude Haiku 5.5 | 74.4 |
| Sonnet 5 | 74.3 |
| GPT-5.5 | 73.7 |
| Grok 4.6 | 73.2 |
| GPT-5.6 Terra | 72.7 |
| Sonnet 4.6 | 72.0 |
| Opus 4.8 | 71.6 |
| Step 5 Preview | 71.4 |
| GLM-5.3 | 71.1 |
| MiMo-V2.6-Flash | 70.3 |
| GPT-6 Luna | 70.1 |
| Opus 4.7 | 70.1 |
| GPT-6 Sol | 70.0 |
| DeepSeek V4.1 Flash | 69.8 |
| Grok 4.7 | 68.6 |
| Qwen3.8-Max | 67.4 |