GDP.pdf (Artificial Analysis, Mean Criteria)
Professional Work
Task-macro mean atomic-criterion pass rate for Artificial Analysis' five-attempt GDP.pdf implementation, with GPT-5.6 Luna Medium judging across 100 tasks. Distinct from the stricter all-pass metric.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-6.1 Sol | 82.9 |
| Claude Opus 5.5 | 82.3 |
| GPT-6 Astra | 82.0 |
| Gemini 4 Carbon | 80.8 |
| Claude Sonnet 5.5 | 80.6 |
| Muse Wonder Full | 80.4 |
| Kimi K3.1 Pro | 80.2 |
| Claude Fable 5.1 | 80.2 |
| Gemini 4 Argon | 79.9 |
| GPT-6.1 Terra | 79.5 |
| Muse Wonder | 79.2 |
| Muse Spark 1.3 | 78.1 |
| GPT-6 Sol | 77.6 |
| GPT-5.6 Sol | 77.6 |
| Claude Haiku 5.5 | 76.7 |
| Qwen3.8 Max (0902) | 76.0 |
| GPT-5.6 Terra | 75.9 |
| Gemini 3.8 Flash | 75.9 |
| Claude Opus 5 | 75.9 |
| Kimi K3 | 75.7 |
| Muse Spark Open | 75.6 |
| GPT-5.6 Luna | 75.5 |
| Muse Spark 1.2 | 75.3 |
| Gemini 3.7 Flash | 75.2 |
| GPT-5.5 | 75.0 |
| Opus 4.8 | 74.9 |
| Qwen3.8-Max | 74.6 |
| Muse Spark 1.1 | 74.2 |
| GPT-6 Luna | 73.9 |
| Grok 4.7 | 71.9 |
| GLM-5.3 Flash | 71.5 |
| MiniMax M3.1 Flash | 71.4 |
| Grok 4.6 | 71.1 |
| Gemini 3.6 Flash | 70.8 |
| DeepSeek V4.1 Flash 1017 | 70.6 |
| GPT-5.5 Instant (2026-06-25 hosted snapshot) | 70.5 |
| Gemini 3.5 Flash | 70.4 |
| Grok 4.5 | 70.3 |
| Mistral Large 4 Preview | 70.2 |
| Qwen3.8 27B | 69.1 |