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 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 | 18th 74.5% | 2nd 82.7% | 9th 77.8% | 14th 76.5% | 7th 79.0% | 16th 75.5% | 17th 75.3% | 19th 74.3% | 21st 71.5% | 5th 79.3% | 5th 79.3% | 15th 76.5% | 4th 79.8% | 8th 78.3% | 1st 83.3% | 12th 77.0% | 9th 77.8% | 13th 76.8% | 3rd 82.0% | 20th 72.2% | 11th 77.5% | |
| 86.2% | 90% | 94% | 91% | 78% | 83% | 65% | 79% | 88% | 79% | 89% | 95% | 83% | 90% | 93% | 91% | 89% | 88% | 85% | 90% | 83% | 87% | |
| 72.7% | 67% | 74% | 72% | 78% | 72% | 82% | 75% | 61% | 59% | 75% | 78% | 68% | 75% | 65% | 82% | 66% | 76% | 82% | 74% | 67% | 78% | |
| 64.3% | 63% | 75% | 65% | 65% | 70% | 67% | 59% | 53% | 57% | 67% | 58% | 58% | 63% | 60% | 72% | 67% | 61% | 63% | 76% | 63% | 69% | |
| 86.6% | 78% | 88% | 83% | 85% | 91% | 88% | 88% | 95% | 91% | 86% | 86% | 97% | 91% | 95% | 88% | 86% | 86% | 77% | 88% | 76% | 76% |