Leaderboard
Vals Finance Index
A composite score for agentic finance work. It averages Finance Agent v2.1 and EMB v1.1 for securities, adds Tax Agent Bench for tax, and weights the two by each sub-sector's share of US GDP (1.6 vs 0.5).
Best reported
66.3
Gemini 4 Carbon
index accuracy %
29 Oct 2026
Vals Finance Index: score vs cost
Score against cost per test. Up and to the left is better.
Updated 29 Oct 2026
Vals Finance Index v1 (released 2026-10-21)
index accuracy %, higher is better. 10 models.
Updated 29 Oct 2026
- Gemini 4 Carbon66.3
- Claude Opus 5.565.6
- Gemini 4 Argon64.9
- Wonder Full64.5
- Claude Sonnet 5.564.5
- Qwen 3.8 Max 090261.7
- Wonder61.2
- DeepSeek V4.1 Flash 101760.9
- GLM 5.360.5
- Gemini 3.8 Flash60.5
Vals Finance Index: cost
cost per test item (USD), lower is better. 10 models.
Updated 29 Oct 2026
- DeepSeek V4.1 Flash 10170.420
- GLM 5.32.2
- Wonder Full3.1
- Wonder3.4
- Gemini 3.8 Flash3.7
- Qwen 3.8 Max 09023.8
- Gemini 4 Carbon6.5
- Gemini 4 Argon6.5
- Claude Sonnet 5.58.3
- Claude Opus 5.511.7
Vals Finance Index v1 (released 2026-10-21)
index accuracy %, higher is better. 10 models.
Updated 29 Oct 2026
- 1Gemini 4 Carbon66.3
- 2Claude Opus 5.565.6
- 3Gemini 4 Argon64.9
- 4Wonder Full64.5
- 5Claude Sonnet 5.564.5
- 6Qwen 3.8 Max 090261.7
- 7Wonder61.2
- 8DeepSeek V4.1 Flash 101760.9
- 9GLM 5.360.5
- 10Gemini 3.8 Flash60.5
| 1 | Gemini 4 Carbon | 66.3 | Default | Vals.ai leaderboard Official board, 29 Oct 2026 | |
|---|---|---|---|---|---|
| 2 | Claude Opus 5.5 | Anthropic | 65.6 | Default | Vals.ai leaderboard Official board, 29 Oct 2026 |
| 3 | Gemini 4 Argon | 64.9 | Default | Vals.ai leaderboard Official board, 29 Oct 2026 | |
| 4 | Wonder Full | Not stated | 64.5 | Default | Vals.ai leaderboard Official board, 29 Oct 2026 |
| 5 | Claude Sonnet 5.5 | Anthropic | 64.5 | Default | Vals.ai leaderboard Official board, 29 Oct 2026 |
| 6 | Qwen 3.8 Max 0902 | Qwen | 61.7 | Default | Vals.ai leaderboard Official board, 29 Oct 2026 |
| 7 | Wonder | Not stated | 61.2 | Default | Vals.ai leaderboard Official board, 29 Oct 2026 |
| 8 | DeepSeek V4.1 Flash 1017 | DeepSeek | 60.9 | Default | Vals.ai leaderboard Official board, 29 Oct 2026 |
| 9 | GLM 5.3 | Zhipu AI | 60.5 | Default | Vals.ai leaderboard Official board, 29 Oct 2026 |
| 10 | Gemini 3.8 Flash | 60.5 | Default | Vals.ai leaderboard Official board, 29 Oct 2026 |
