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 Chile. 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 | 18th 77.8% | 1st 85.8% | 11th 80.3% | 19th 76.5% | 8th 81.0% | 21st 76.3% | 6th 81.8% | 12th 80.0% | 13th 79.5% | 19th 76.5% | 9th 80.8% | 15th 78.5% | 4th 82.5% | 14th 78.8% | 7th 81.5% | 5th 82.0% | 17th 78.3% | 15th 78.5% | 3rd 83.8% | 2nd 85.0% | 10th 80.8% | |
| 81.4% | 77% | 91% | 78% | 76% | 72% | 67% | 88% | 75% | 85% | 78% | 79% | 74% | 89% | 76% | 84% | 96% | 88% | 77% | 93% | 84% | 82% | |
| 80.8% | 76% | 89% | 85% | 73% | 80% | 89% | 77% | 84% | 74% | 72% | 85% | 81% | 85% | 82% | 85% | 72% | 83% | 89% | 77% | 84% | 74% | |
| 74.1% | 73% | 81% | 84% | 82% | 75% | 72% | 79% | 75% | 69% | 69% | 80% | 76% | 74% | 60% | 75% | 69% | 63% | 63% | 80% | 79% | 79% | |
| 84.8% | 85% | 82% | 74% | 75% | 97% | 77% | 83% | 86% | 90% | 87% | 79% | 83% | 82% | 97% | 82% | 91% | 79% | 85% | 85% | 93% | 88% |