Finance Agent v2 (Vals Index subset)
Professional Work · 2026-07-01
Finance Agent v2 evaluated on the Vals Index subset using the benchmark's shared six-tool agent harness and partial-credit metric. Vals reports the component as an average over three model runs; it remains a protocol-specific child rather than being relabeled as the full benchmark.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 3.5 Flash | 58.1 |
| Muse Spark 1.1 | 57.1 |
| Claude Opus 5 | 56.6 |
| Claude Fable 5 | 56.3 |
| Kimi K3 | 55.9 |
| GPT-5.6 Luna | 55.6 |
| Gemini 3.6 Flash | 55.3 |
| GPT-5.6 Sol | 55.0 |
| Opus 4.8 | 53.9 |
| GPT-5.6 Terra | 52.6 |
| Sonnet 5 | 52.0 |
| GPT-5.5 | 51.8 |
| Opus 4.7 | 51.5 |
| Sonnet 4.6 | 51.0 |
| GLM-5.2 | 50.8 |
| Grok 4.5 | 48.8 |
| Qwen3.7-Max | 48.4 |
| MiniMax M3 | 48.0 |
| Gemini 3.5 Flash-Lite | 46.6 |
| Inkling | 46.0 |
| GPT-5.4 Mini | 45.4 |
| Kimi K2.6 | 44.9 |
| GLM-5.1 | 44.8 |
| DeepSeek-V4-Pro | 44.1 |
| Gemini 3.1 Pro Preview | 43.0 |
| Gemini 3 Flash Preview | 42.5 |
| Inkling-Small | 42.1 |
| Qwen3.7-Plus | 41.2 |
| MiMo-V2.5-Pro | 41.2 |
| Qwen3.6 Plus (2026-04-02) | 40.9 |
| GPT-5.4 Nano | 38.2 |
| Nemotron 3 Ultra 550B A55B | 38.2 |
| Grok 4.3 | 37.8 |
| MiMo-V2.5 | 37.6 |
| Mistral Medium 3.5 | 31.5 |
| Haiku 4.5 | 31.0 |
| Gemini 3.1 Flash-Lite Preview | 30.1 |
| Grok 4.20 | 28.6 |
| MiniMax M2.7 | 27.9 |
| Laguna M.1 | 24.6 |