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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 82.8% | 2nd 84.3% | 14th 78.3% | 4th 82.8% | 19th 70.3% | 15th 74.3% | 17th 72.8% | 18th 72.3% | 16th 73.3% | 9th 81.0% | 10th 80.8% | 20th 64.5% | 11th 80.0% | 6th 82.7% | 21st 60.5% | 8th 82.3% | 13th 79.3% | 3rd 84.2% | 12th 79.8% | 7th 82.5% | 1st 84.5% | |
| 70.1% | 77% | 78% | 62% | 80% | 70% | 52% | 65% | 74% | 63% | 79% | 83% | 38% | 80% | 92% | 0% | 80% | 86% | 82% | 75% | 77% | 80% | |
| 80.5% | 84% | 82% | 84% | 84% | 84% | 77% | 82% | 73% | 67% | 81% | 84% | 84% | 84% | 77% | 84% | 84% | 72% | 84% | 77% | 80% | 83% | |
| 85.2% | 91% | 97% | 89% | 89% | 86% | 91% | 67% | 76% | 88% | 91% | 78% | 67% | 78% | 84% | 78% | 87% | 78% | 94% | 97% | 95% | 89% | |
| 75.1% | 79% | 80% | 78% | 78% | 41% | 77% | 77% | 66% | 75% | 73% | 78% | 69% | 78% | 78% | 80% | 78% | 81% | 77% | 70% | 78% | 86% |