Finance Agent v2 - Earnings Analysis
Professional Work · 2026-05-19
The Earnings 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 4 Argon | 84.8 |
| Gemini 3.8 Flash | 81.4 |
| Muse Spark Open | 80.3 |
| Gemini 3.7 Flash | 79.1 |
| Gemini 3.5 Flash | 79.0 |
| GLM-5.3 | 78.7 |
| Muse Wonder Full | 78.6 |
| MiMo-V2.6-Pro | 77.7 |
| Muse Spark 1.2 | 77.3 |
| GPT-5.6 Terra | 77.3 |
| Muse Spark 1.3 | 77.2 |
| Qwen3.8 Max (0902) | 77.1 |
| Muse Wonder | 76.8 |
| Mistral Large 4 Preview | 76.5 |
| Muse Spark 1.1 | 76.2 |
| Claude Fable 5.1 | 75.5 |
| Gemini 3.6 Flash | 75.3 |
| DeepSeek V4.1 Flash 1017 | 75.3 |
| Hy4 Preview | 75.1 |
| GPT-5.6 Luna | 74.9 |
| Grok 4.7 | 74.6 |
| MiMo-V2.6-Flash | 74.5 |
| GPT-5.6 Sol | 74.4 |
| GPT-6 Luna | 74.2 |
| Grok 4.6 | 73.9 |
| Claude Haiku 5.5 | 73.5 |
| GPT-5.5 | 73.2 |
| GLM-5.3 Flash | 72.9 |
| DeepSeek V4.1 Flash | 72.9 |
| Sonnet 5 | 72.6 |
| GPT-6 Sol | 72.4 |
| Opus 4.8 | 72.1 |
| Step 5 Preview | 71.7 |
| Opus 4.7 | 71.6 |
| GPT-6.1 Sol | 71.5 |
| Qwen3.8 27B | 70.9 |
| Grok 4.5 | 70.8 |
| DeepSeek-V4-Flash-0731 | 69.8 |
| GPT-6 Astra | 69.5 |
| Kimi K3 | 69.4 |