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 Brazil. 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 | 2nd 82.3% | 5th 79.5% | 3rd 81.0% | 14th 76.5% | 10th 77.8% | 16th 74.8% | 11th 77.5% | 15th 75.0% | 21st 72.5% | 20th 72.8% | 9th 78.0% | 12th 77.0% | 1st 82.5% | 18th 73.5% | 13th 76.8% | 8th 78.3% | 6th 79.0% | 17th 74.0% | 4th 80.0% | 7th 78.5% | 19th 73.3% | |
| 87.1% | 94% | 93% | 94% | 91% | 88% | 65% | 87% | 78% | 88% | 86% | 93% | 86% | 95% | 78% | 94% | 95% | 88% | 81% | 89% | 87% | 79% | |
| 71.8% | 76% | 78% | 74% | 72% | 69% | 80% | 71% | 75% | 57% | 57% | 67% | 75% | 81% | 67% | 69% | 65% | 78% | 78% | 75% | 74% | 69% | |
| 63.7% | 65% | 71% | 68% | 65% | 63% | 66% | 70% | 59% | 53% | 57% | 76% | 66% | 68% | 58% | 65% | 58% | 59% | 55% | 67% | 65% | 64% | |
| 86.0% | 94% | 76% | 88% | 78% | 91% | 88% | 82% | 88% | 92% | 91% | 76% | 81% | 86% | 91% | 79% | 95% | 91% | 82% | 89% | 88% | 81% |