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 | 6th 82.5% | 1st 84.3% | 15th 79.0% | 3rd 82.8% | 16th 76.3% | 17th 74.3% | 21st 71.5% | 20th 72.0% | 19th 73.5% | 7th 81.8% | 10th 81.3% | 18th 73.8% | 14th 79.3% | 9th 81.5% | 2nd 83.0% | 11th 81.0% | 5th 82.7% | 13th 80.3% | 11th 81.0% | 4th 82.8% | 8th 81.5% | |
| 76.1% | 77% | 78% | 62% | 80% | 80% | 52% | 60% | 76% | 70% | 75% | 83% | 80% | 75% | 89% | 83% | 78% | 86% | 79% | 75% | 80% | 80% | |
| 80.9% | 84% | 82% | 84% | 84% | 84% | 77% | 82% | 73% | 67% | 84% | 84% | 84% | 84% | 84% | 84% | 80% | 83% | 75% | 82% | 77% | 80% | |
| 85.0% | 91% | 97% | 89% | 89% | 88% | 91% | 67% | 76% | 86% | 93% | 80% | 53% | 87% | 84% | 88% | 88% | 84% | 89% | 97% | 88% | 80% | |
| 75.3% | 78% | 80% | 81% | 78% | 53% | 77% | 77% | 63% | 71% | 75% | 78% | 78% | 71% | 69% | 77% | 78% | 78% | 78% | 70% | 86% | 86% |