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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 9th 81.3% | 6th 82.3% | 2nd 84.0% | 14th 78.3% | 16th 76.0% | 17th 75.3% | 1st 86.0% | 21st 71.5% | 18th 75.0% | 18th 75.0% | 11th 80.8% | 5th 82.5% | 9th 81.3% | 20th 73.8% | 13th 79.3% | 8th 82.0% | 15th 77.5% | 4th 83.0% | 3rd 83.5% | 6th 82.3% | 12th 79.5% | |
| 76.8% | 75% | 79% | 78% | 62% | 71% | 52% | 85% | 60% | 78% | 70% | 85% | 79% | 83% | 80% | 79% | 89% | 86% | 82% | 82% | 80% | 77% | |
| 80.7% | 84% | 82% | 82% | 84% | 83% | 81% | 89% | 82% | 73% | 67% | 71% | 84% | 84% | 84% | 82% | 84% | 77% | 77% | 84% | 82% | 79% | |
| 85.4% | 91% | 97% | 96% | 89% | 97% | 91% | 89% | 67% | 78% | 88% | 86% | 88% | 80% | 53% | 78% | 84% | 78% | 95% | 96% | 89% | 84% | |
| 75.1% | 75% | 71% | 80% | 78% | 53% | 77% | 81% | 77% | 71% | 75% | 81% | 79% | 78% | 78% | 78% | 71% | 69% | 78% | 72% | 78% | 78% |