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 | 3rd 82.5% | 1st 84.3% | 14th 78.3% | 2nd 82.8% | 17th 74.0% | 16th 74.3% | 19th 72.0% | 20th 71.2% | 18th 73.8% | 6th 82.0% | 8th 80.8% | 21st 60.3% | 12th 79.0% | 9th 80.3% | 15th 77.5% | 9th 80.3% | 11th 79.3% | 7th 81.3% | 4th 82.3% | 5th 82.2% | 13th 78.8% | |
| 73.7% | 79% | 78% | 62% | 80% | 80% | 52% | 60% | 73% | 73% | 79% | 83% | 38% | 75% | 89% | 77% | 76% | 86% | 82% | 80% | 66% | 80% | |
| 79.6% | 84% | 82% | 84% | 84% | 82% | 77% | 84% | 73% | 67% | 84% | 82% | 67% | 82% | 77% | 83% | 80% | 75% | 83% | 82% | 80% | 80% | |
| 83.5% | 89% | 97% | 89% | 89% | 88% | 91% | 67% | 76% | 78% | 86% | 80% | 67% | 81% | 84% | 69% | 88% | 78% | 82% | 97% | 97% | 80% | |
| 75.0% | 78% | 80% | 78% | 78% | 46% | 77% | 77% | 63% | 77% | 79% | 78% | 69% | 78% | 71% | 81% | 77% | 78% | 78% | 70% | 86% | 75% |