Benchmarks · Professional work · Agents & computer use
Finance Agent v2.1
An agent does the core tasks of a financial analyst. Share correct. Version 2.1, the one inside the Vals Index; its own page still shows version 2. From Vals AI.
29 models · 29 results · updated 2026-11-11 · vals.ai ↗
Leaderboard
Fable 5.2 high
Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's median subscription plan, or API price with no plan data. 14 more models under All models in settings.
More from this benchmark
1 published measuresTime per task37 results · lower is better
15 more models under All models in settings.
All results
29 rows| # | Model | Effort | Finance Agent v2.1 | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Fable 5.2 | high | 69.5% | $0.18 | $4.83 | 3.5 min |
| 2 | Opus 5.5 | max | 67.8% | $0.13 | $8.91 | 33 min |
| 3 | Gemini 4 Argon | high | 67.7% | $3.08 | $4.32 | 13 min |
| 4 | Inkling 2 Small | max | 67.5% | free | $0.18 | 4.9 min |
| 5 | Sonnet 5.5 | max | 67.3% | $0.11 | $6.95 | 34 min |
| 6 | Gemini 4 Carbon | high | 67.2% | $5.20 | $7.29 | 30 min |
| 7 | Gemini 3.8 Flash | high | 65.8% | $0.081 | $1.99 | 7.4 min |
| 8 | Haiku 5.5 | max | 65.4% | $0.035 | $1.64 | 31 min |
| 9 | Gemini 4 Hydrogen | xhigh | 65.1% | $3.11 | $4.36 | 18 min |
| 10 | GLM 5.3 | max | 65.0% | $0.11 | $1.03 | 20 min |
| 11 | Hy4 | high | 64.7% | $0.37 | $1.28 | 37 min |
| 12 | MiMo V2.6 Pro | max | 64.3% | $0.15 | $0.18 | 11 min |
| 13 | Muse Ember | max | 63.8% | $0.056 | $0.056 | 89s |
| 14 | MiMo V2.6 Flash | high | 63.3% | free | $0.067 | 16 min |
| 15 | DeepSeek V4.1 Flash 1017 | max | 62.9% | free | $0.47 | 15 min |
| 16 | GPT-6.1 Sol | max | 61.8% | $0.054 | $1.63 | 19 min |
| 17 | Hy4 preview | high | 61.6% | $0.50 | $0.67 | 25 min |
| 18 | Muse Spark Open | xhigh | 60.7% | $2.76 | $2.76 | 27 min |
| 19 | GLM 5.3 Flash | max | 60.6% | free | $0.072 | 4.9 min |
| 20 | Grok 4.7 | xhigh | 60.6% | $0.21 | $2.24 | 11 min |
| 21 | GPT-6 Astra | max | 60.4% | $0.33 | $7.82 | 20 min |
| 22 | Kimi K3 | max | 60.0% | $0.17 | $1.88 | 15 min |
| 23 | Step 5 Preview | high | 58.9% | $0.58 | $0.58 | 9.0 min |
| 24 | DeepSeek V4 Pro 0813 | max | 57.1% | $0.82 | $0.82 | 7.9 min |
| 25 | GPT-6 Luna | max | 56.8% | $0.009 | $0.12 | 15 min |
| 26 | GPT-6.1 Terra | max | 56.0% | $0.073 | $1.92 | 30 min |
| 27 | Mercury 3 | high | 54.7% | $0.065 | $0.065 | 3.9 min |
| 28 | Inkling | max | 49.9% | $0.082 | $0.89 | 9.6 min |
| 29 | Inkling Small | max | 44.8% | $0.17 | $0.21 | 5.2 min |