Benchmarks · economics
Finance Agent v2
Evaluating agents on core financial analyst tasks using the FAB v2 harness
60 models · 61 results · updated 2026-10-29 · vals.ai ↗
Leaderboard
Gemini 4 Argon 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. 47 more models under All models in settings.
More from this benchmark
1 published measuresTime per task81 results · lower is better
45 more models under All models in settings.
All results
61 rows| # | Model | Effort | Finance Agent v2 | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argon | high | 65.4% | $3.12 | $4.38 | 16 min |
| 2 | Gemini 3.8 Flash | high | 61.4% | $0.081 | $2.00 | 3.3 min |
| 3 | Muse Spark Open | xhigh | 61.3% | $0.77 | $0.77 | 24 min |
| 4 | Muse Spark 1.2 | xhigh | 60.6% | $0.38 | $0.77 | 5.1 min |
| 5 | Muse Spark 1.3 | max | 60.0% | $0.38 | $0.76 | 3.3 min |
| 6 | Gemini 3.7 Flash | high | 59.0% | $0.19 | $1.48 | 3.0 min |
| 7 | Muse Spark 1.3 | xhigh | 58.9% | $0.37 | $0.74 | 5.7 min |
| 8 | Fable 5.1 | max | 58.9% | $1.30 | $8.35 | 18 min |
| 9 | Opus 5 | max | 58.6% | $0.089 | $5.12 | 10.0 min |
| 10 | Opus 5.5 | max | 58.6% | $0.14 | $9.22 | 33 min |
| 11 | Sonnet 5.5 | max | 58.1% | $0.099 | $6.55 | 32 min |
| 12 | Gemini 3.5 Flash | high | 57.9% | $2.51 | $2.51 | 5.4 min |
| 13 | GLM 5.3 Flash | max | 57.9% | free | $0.095 | 15 min |
| 14 | MiMo V2.6 Pro | max | 57.3% | $0.17 | $0.20 | 11 min |
| 15 | Muse Spark 1.1 | xhigh | 57.2% | $0.72 | $0.72 | 6.9 min |
| 16 | DeepSeek V4.1 Flash 1017 | max | 57.0% | free | $0.46 | 15 min |
| 17 | Fable 5 | max | 56.3% | $0.91 | $8.06 | 10 min |
| 18 | Gemini 3.6 Flash | high | 56.3% | $0.044 | $1.40 | 3.7 min |
| 19 | MiMo V2.6 Flash | high | 56.3% | free | $0.072 | 7.0 min |
| 20 | GLM 5.3 | max | 55.8% | $0.11 | $1.07 | 16 min |
| 21 | Hy4 preview | high | 55.1% | $0.45 | $0.59 | 24 min |
| 22 | GPT-5.6 Luna | max | 55.0% | $0.013 | $0.28 | 13 min |
| 23 | GPT-5.6 Terra | max | 54.4% | $0.10 | $3.63 | 24 min |
| 24 | Haiku 5.5 | max | 54.1% | $0.035 | $1.64 | 31 min |
| 25 | Opus 4.8 | max | 53.9% | $0.073 | $4.22 | 9.1 min |
| 26 | Sonnet 5 | max | 53.9% | $0.013 | $0.75 | 13 min |
| 27 | GPT-5.6 Sol | max | 53.8% | $0.035 | $1.25 | 19 min |
| 28 | Grok 4.6 | high | 53.7% | $0.17 | $1.66 | 17 min |
| 29 | GPT-6 Astra | max | 53.5% | $0.29 | $6.82 | 12 min |
| 30 | DeepSeek V4.1 Flash | high | 53.5% | $0.015 | $0.21 | 6.1 min |