Benchmarks · economics
Excel Modeling Benchmark
Evaluating agents on Excel-based financial modeling tasks
57 models · 58 results · updated 2026-10-20 · vals.ai ↗
Leaderboard
Fable 5.1 max
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. 44 more models under All models in settings.
More from this benchmark
1 published measuresTime per task77 results · lower is better
41 more models under All models in settings.
All results
58 rows| # | Model | Effort | Excel Modeling Benchmark | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Fable 5.1 | max | 76.7% | $2.48 | $16 | 30 min |
| 2 | Opus 5.5 | max | 75.9% | $0.17 | $11 | 35 min |
| 3 | Sonnet 5.5 | max | 75.7% | $0.13 | $8.79 | 37 min |
| 4 | Gemini 4 Argon | high | 75.2% | $8.41 | $12 | 38 min |
| 5 | Fable 5 | max | 73.7% | $1.39 | $12 | 27 min |
| 6 | Opus 5 | max | 73.6% | $0.14 | $8.02 | 26 min |
| 7 | GPT-5.6 Sol | max | 72.3% | $0.17 | $6.01 | 9.8 min |
| 8 | Gemini 3.8 Flash | high | 72.2% | $0.33 | $8.24 | 13 min |
| 9 | GPT-6 Astra | max | 71.7% | $0.25 | $5.83 | 13 min |
| 10 | GPT-6 Sol | max | 71.5% | $0.039 | $1.28 | 10 min |
| 11 | Gemini 3.7 Flash | high | 71.3% | $0.74 | $5.69 | 11 min |
| 12 | GPT-6.1 Sol | max | 70.8% | $0.067 | $1.14 | 18 min |
| 13 | Opus 4.8 | max | 69.4% | $0.21 | $12 | 44 min |
| 14 | GPT-6 Luna | max | 68.5% | $0.010 | $0.14 | 17 min |
| 15 | Muse Spark 1.3 | max | 67.4% | $1.27 | $2.55 | 14 min |
| 16 | GPT-5.6 Luna | max | 67.1% | $0.017 | $0.37 | 11 min |
| 17 | Grok 4.7 | xhigh | 67.0% | $0.60 | $6.48 | 35 min |
| 18 | Kimi K3 | max | 66.7% | $0.28 | $3.07 | 12 min |
| 19 | Sonnet 5 | max | 66.3% | $0.18 | $10 | 50 min |
| 20 | GPT-5.6 Terra | max | 66.2% | $0.061 | $2.19 | 14 min |
| 21 | MiMo V2.6 Flash | high | 65.5% | free | $0.11 | 25 min |
| 22 | Gemini 3.6 Flash | high | 65.4% | $0.12 | $3.89 | 12 min |
| 23 | GPT-5.5 | xhigh | 64.5% | $0.090 | $3.27 | 15 min |
| 24 | Opus 4.7 | max | 63.7% | $13 | $13 | 39 min |
| 25 | Gemini 3.5 Flash | high | 63.5% | $5.17 | $5.17 | 19 min |
| 26 | MiMo V2.6 Pro | max | 62.9% | $0.28 | $0.33 | 55 min |
| 27 | Grok 4.6 | high | 62.7% | $0.31 | $3.06 | 53 min |
| 28 | Muse Spark 1.3 | xhigh | 62.7% | $1.78 | $3.55 | 23 min |
| 29 | DeepSeek V4.1 Flash 1017 | max | 61.8% | free | $0.36 | 17 min |
| 30 | GLM 5.2 | max | 61.5% | $0.13 | $4.47 | 59 min |