Finance Agent v2 - Financial Modeling
Professional Work · 2026-05-19
The Financial Modeling 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 |
|---|---|
| Muse Spark 1.2 | 34.5 |
| Muse Spark Open | 34.4 |
| Muse Spark 1.1 | 34.1 |
| Muse Spark 1.3 | 33.5 |
| Gemini 3.8 Flash | 32.6 |
| Gemini 4 Argon | 29.8 |
| Gemini 3.5 Flash | 29.4 |
| Claude Haiku 5.5 | 28.3 |
| GLM-5.3 Flash | 25.4 |
| Claude Fable 5.1 | 25.3 |
| Gemini 3.6 Flash | 25.1 |
| MiMo-V2.6-Pro | 24.8 |
| MiMo-V2.6-Flash | 24.2 |
| Sonnet 5 | 24.2 |
| Gemini 3.7 Flash | 24.2 |
| Muse Wonder Full | 23.7 |
| Kimi K3 | 23.6 |
| Opus 4.8 | 23.3 |
| Ember-1 | 23.2 |
| GPT-6.1 Sol | 23.1 |
| DeepSeek V4.1 Flash | 23.1 |
| GPT-5.6 Terra | 23.0 |
| GPT-5.5 | 22.9 |
| Qwen3.8 Max (0902) | 22.8 |
| DeepSeek V4.1 Flash 1017 | 22.8 |
| Muse Wonder | 22.5 |
| GPT-6 Luna | 22.5 |
| GLM-5.3 | 22.1 |
| GPT-5.6 Luna | 21.6 |
| GPT-6 Astra | 21.6 |
| Hy4 Preview | 20.9 |
| GPT-5.6 Sol | 20.7 |
| Mistral Large 4 Preview | 20.5 |
| Qwen3.8-Max | 20.4 |
| Opus 4.7 | 20.1 |
| DeepSeek-V4-Flash-0731 | 19.8 |
| GPT-5.4 Mini | 19.6 |
| Gemini 3.5 Flash-Lite | 19.3 |
| GPT-6 Sol | 19.3 |
| Qwen3.8 27B | 19.3 |