Vals Index v2
Indexes · 2026-08-13
Vals Index v2 combines sector means with GDP weights 8.0 for finance, 5.6 for coding and 1.2 for legal, divided by 14.8. Finance averages Finance Agent v2 and EMB; coding averages Terminal-Bench 2.1, Vibe Code Bench and the Code Migration subset; legal averages Legal Research and HLAB. The changed composition is kept separate from the earlier index.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-6 Astra | 66.6 |
| Muse Spark 1.3 | 64.5 |
| GPT-5.6 Sol | 63.7 |
| GPT-6 Sol | 62.6 |
| Gemini 3.8 Flash | 62.3 |
| Opus 4.8 | 60.9 |
| Grok 4.7 | 60.2 |
| GPT-5.6 Luna | 59.9 |
| Sonnet 5 | 59.6 |
| GPT-5.6 Terra | 59.6 |
| MiMo-V2.6-Flash | 59.6 |
| MiMo-V2.6-Pro | 59.5 |
| Gemini 3.7 Flash | 59.3 |
| Grok 4.6 | 59.2 |
| GPT-6 Luna | 58.5 |
| DeepSeek V4.1 Flash | 57.9 |
| Kimi K3 | 57.8 |
| GPT-5.5 | 57.4 |
| Muse Spark 1.2 | 57.1 |
| GLM-5.3 | 57.0 |
| Opus 4.7 | 56.1 |
| Hy4 Preview | 55.4 |
| Gemini 3.6 Flash | 55.4 |
| Muse Spark 1.1 | 54.8 |
| DeepSeek-V4-Flash-0731 | 53.6 |
| GLM-5.2 | 53.1 |
| Gemini 3.5 Flash | 53.1 |
| DeepSeek V4 Pro 0813 | 52.4 |
| Qwen3.8-Max | 51.8 |
| Grok 4.5 | 51.5 |
| Sonnet 4.6 | 50.6 |
| Qwen3.8 27B | 48.5 |
| GLM-5.3 Flash | 47.2 |
| Qwen3.7-Max (source unspecified) | 44.8 |
| Kimi K2.6 | 43.5 |
| DeepSeek-V4-Pro | 42.9 |
| MiniMax M3 | 42.7 |
| Gemini 3.1 Pro Preview | 41.9 |
| MiMo-V2.5-Pro | 41.0 |
| MiMo-V2.5 | 39.9 |