Loading blueprint versions...
Please wait while we gather all the unique runs for this blueprint.
Please wait while we gather all the unique runs for this blueprint.
Please wait while we prepare the detailed comparison.
DTEF: Predict response distributions for Morocco. Source: Global Dialogues GD1 (https://github.com/collect-intel/global-dialogues)
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude 3.7 Sonnet | Claude Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT 5 | GPT 5.1 | GPT OSS 120b | GPT OSS 20b | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 10th 80.3% | 5th 82.3% | 13th 79.0% | 3rd 82.8% | 18th 73.8% | 16th 74.3% | 20th 72.8% | 17th 74.0% | 18th 73.8% | 8th 81.5% | 9th 81.3% | 21st 67.3% | 15th 76.5% | 10th 80.3% | 5th 82.3% | 10th 80.3% | 14th 77.5% | 5th 82.3% | 3rd 82.8% | 2nd 83.0% | 1st 84.7% | |
| 75.3% | 73% | 70% | 62% | 80% | 75% | 52% | 65% | 76% | 73% | 79% | 83% | 70% | 75% | 89% | 79% | 73% | 83% | 82% | 80% | 82% | 80% | |
| 79.5% | 84% | 82% | 84% | 84% | 84% | 77% | 82% | 73% | 67% | 84% | 84% | 54% | 82% | 77% | 84% | 84% | 75% | 80% | 84% | 80% | 85% | |
| 84.7% | 89% | 97% | 89% | 89% | 86% | 91% | 67% | 76% | 78% | 86% | 80% | 67% | 78% | 84% | 86% | 89% | 81% | 89% | 97% | 84% | 95% | |
| 75.2% | 75% | 80% | 81% | 78% | 50% | 77% | 77% | 71% | 77% | 77% | 78% | 78% | 71% | 71% | 80% | 75% | 71% | 78% | 70% | 86% | 79% |