Benchmarks · economics
GDP.pdf
GDP.pdf: document-heavy professional tasks over PDFs graded against rubric criteria; share of tasks passing all criteria.
102 models · 187 results · data as of 2026-11-06 · artificialanalysis.ai ↗
Leaderboard
GPT-6 Astra xhigh
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. 26 more models under All models in settings.
All results
187 rows| # | Model | Effort | GDP.pdf | Subscription $ / task | API $ / task |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | xhigh | 32.2% | $0.082 | $1.91 |
| 2 | GPT-6.1 Sol | high | 32.0% | $0.020 | $0.35 |
| 3 | GPT-6.1 Sol | xhigh | 31.8% | $0.021 | $0.37 |
| 4 | Kimi K3.1 | max | 31.4% | $0.52 | $0.52 |
| 5 | GPT-6 Astra | high | 31.0% | $0.077 | $1.79 |
| 6 | GPT-6 Astra | max | 31.0% | $0.089 | $2.08 |
| 7 | GPT-6.1 Sol | max | 31.0% | $0.024 | $0.42 |
| 8 | Muse Wonder (Max) | max | 30.6% | $0.48 | $0.72 |
| 9 | GPT-6 Astra | low | 30.4% | $0.073 | $1.70 |
| 10 | GPT-6 Astra | medium | 30.4% | $0.074 | $1.72 |
| 11 | GPT-6.1 Sol | medium | 30.0% | $0.020 | $0.34 |
| 12 | Gemini 4 Carbon | medium | 29.6% | $0.17 | $0.48 |
| 13 | Opus 5.5 | high | 28.8% | $0.012 | $0.83 |
| 14 | Gemini 4 Carbon | low | 28.6% | $0.14 | $0.38 |
| 15 | GPT-6.1 Terra | max | 28.6% | $0.012 | $0.24 |
| 16 | Gemini 4 Carbon | high | 28.4% | $0.30 | $0.85 |
| 17 | GPT-6.1 Terra | medium | 28.4% | $0.008 | $0.17 |
| 18 | Fable 5.1 | low | 28.0% | $0.30 | $1.91 |
| 19 | GPT-6.1 Terra | high | 28.0% | $0.009 | $0.17 |
| 20 | GPT-5.6 Sol | high | 27.8% | ||
| 21 | GPT-5.6 Sol | xhigh | 27.6% | ||
| 22 | GPT-5.6 Sol | max | 27.2% | ||
| 23 | GPT-6.1 Sol | low | 27.0% | $0.019 | $0.33 |
| 24 | Fable 5.1 | high | 26.8% | $0.31 | $2.00 |
| 25 | Fable 5.1 | medium | 26.8% | $0.30 | $1.95 |
| 26 | Opus 5.5 | xhigh | 26.6% | $0.015 | $0.96 |
| 27 | GPT-6.1 Terra | xhigh | 26.6% | $0.009 | $0.18 |
| 28 | Muse Spark 1.3 | max | 26.6% | $0.10 | $0.21 |
| 29 | Fable 5.1 | max | 26.2% | $0.43 | $2.76 |
| 30 | Fable 5.1 | xhigh | 26.2% | $0.36 | $2.31 |