Benchmarks · economics
Finance Agent v2
Evaluating agents on core financial analyst tasks using the FAB v2 harness
59 models · 60 results · updated 2026-10-20 · vals.ai ↗
Leaderboard
Gemini 4 Argon high
More from this benchmark
1 published measuresTime per task81 results · lower is better
All results
60 rows| # | Model | Effort | Finance Agent v2 | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argon | high | 65.4% | $1.56 | $4.38 | 16 min |
| 2 | Gemini 3.8 Flash | high | 61.4% | $0.081 | $2.00 | 3.3 min |
| 3 | Muse Spark 1.2 | xhigh | 60.6% | $0.38 | $0.77 | 5.1 min |
| 4 | Muse Spark 1.3 | max | 60.0% | $0.38 | $0.76 | 3.3 min |
| 5 | Gemini 3.7 Flash | high | 59.0% | $0.19 | $1.48 | 3.0 min |
| 6 | Muse Spark 1.3 | xhigh | 58.9% | $0.37 | $0.74 | 5.7 min |
| 7 | Fable 5.1 | max | 58.9% | $1.30 | $8.35 | 18 min |
| 8 | Opus 5 | max | 58.6% | $0.089 | $5.12 | 10.0 min |
| 9 | Opus 5.5 | max | 58.6% | $0.14 | $9.22 | 33 min |
| 10 | Sonnet 5.5 | max | 58.1% | $0.099 | $6.55 | 32 min |
| 11 | Gemini 3.5 Flash | high | 57.9% | $2.51 | $2.51 | 5.4 min |
| 12 | GLM 5.3 Flash | max | 57.9% | free | $0.048 | 15 min |
| 13 | MiMo V2.6 Pro | high | 57.3% | $0.17 | $0.20 | 11 min |
| 14 | Muse Spark 1.1 | xhigh | 57.2% | $0.72 | $0.72 | 6.9 min |
| 15 | DeepSeek V4.1 Flash 1017 | max | 57.0% | free | $0.46 | 15 min |
| 16 | Fable 5 | max | 56.3% | $0.91 | $8.06 | 10 min |
| 17 | Gemini 3.6 Flash | high | 56.3% | $0.044 | $1.40 | 3.7 min |
| 18 | MiMo V2.6 Flash | high | 56.3% | free | $0.072 | 7.0 min |
| 19 | GLM 5.3 | max | 55.8% | $0.11 | $1.07 | 16 min |
| 20 | GPT-5.6 Luna | max | 55.0% | $0.026 | $0.28 | 13 min |
| 21 | Mistral Large 4 | high | 54.7% | $1.20 | $1.20 | 26 min |
| 22 | GPT-5.6 Terra | max | 54.4% | $0.20 | $3.63 | 24 min |
| 23 | Haiku 5.5 | max | 54.1% | $0.035 | $1.64 | 31 min |
| 24 | Opus 4.8 | max | 53.9% | $0.073 | $4.22 | 9.1 min |
| 25 | Sonnet 5 | max | 53.9% | $0.013 | $0.75 | 13 min |
| 26 | GPT-5.6 Sol | max | 53.8% | $0.069 | $1.25 | 19 min |
| 27 | Grok 4.6 | high | 53.7% | $0.17 | $1.66 | 17 min |
| 28 | GPT-6 Astra | max | 53.5% | $0.58 | $6.82 | 12 min |
| 29 | DeepSeek V4.1 Flash | high | 53.5% | $0.013 | $0.21 | 6.1 min |
| 30 | Kimi K3 | max | 53.1% | $0.15 | $1.91 | 4.8 min |