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 3.5 Flash | 79.0 |
| Claude Fable 5 | 77.3 |
| Muse Spark 1.1 | 76.2 |
| Gemini 3.6 Flash | 75.3 |
| GPT-5.6 Luna | 74.9 |
| GPT-5.6 Sol | 74.4 |
| Claude Opus 5 | 73.8 |
| GPT-5.6 Terra | 73.7 |
| GPT-5.5 | 73.2 |
| Kimi K3 | 73.1 |
| Sonnet 5 | 72.6 |
| Opus 4.8 | 72.1 |
| Opus 4.7 | 71.6 |
| Grok 4.5 | 70.8 |
| GLM-5.2 | 66.6 |
| MiniMax M3 | 66.2 |
| GPT-5.4 Mini | 65.3 |
| Sonnet 4.6 | 65.1 |
| Gemini 3.1 Pro Preview | 64.7 |
| Gemini 3.5 Flash-Lite | 64.4 |
| Kimi K2.6 | 63.8 |
| Gemini 3 Flash Preview | 62.1 |
| Inkling | 60.4 |
| Qwen3.7-Max | 60.2 |
| DeepSeek-V4-Pro | 59.8 |
| GLM-5.1 | 57.0 |
| MiMo-V2.5-Pro | 54.6 |
| Qwen3.6 Plus (2026-04-02) | 52.4 |
| Qwen3.7-Plus | 50.3 |
| Grok 4.3 | 47.7 |
| GPT-5.4 Nano | 45.6 |
| MiMo-V2.5 | 45.0 |
| Mistral Medium 3.5 | 42.1 |
| Nemotron 3 Ultra 550B A55B | 40.6 |
| Grok 4.20 | 34.4 |
| MiniMax M2.7 | 31.8 |
| Gemini 3.1 Flash-Lite Preview | 31.3 |
| Haiku 4.5 | 26.7 |
| Laguna M.1 | 25.9 |
| Laguna XS.2 | 15.3 |