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 | 9th 77.0% | 1st 82.7% | 7th 78.3% | 10th 76.5% | 13th 76.3% | 16th 74.3% | 14th 74.5% | 15th 74.5% | 18th 72.5% | 5th 79.8% | 6th 78.8% | 11th 76.5% | 8th 77.3% | 12th 76.3% | 2nd 82.5% | 3rd 82.3% | 17th 73.3% | 19th 72.3% | 4th 80.5% | 20th 72.2% | 21st 71.8% | |
| 85.3% | 94% | 94% | 91% | 78% | 83% | 65% | 78% | 88% | 83% | 93% | 95% | 83% | 94% | 85% | 89% | 93% | 85% | 76% | 90% | 81% | 74% | |
| 71.2% | 71% | 80% | 72% | 78% | 65% | 78% | 73% | 57% | 59% | 73% | 76% | 65% | 73% | 69% | 75% | 77% | 69% | 78% | 74% | 67% | 67% | |
| 64.1% | 65% | 69% | 65% | 65% | 70% | 66% | 59% | 58% | 57% | 67% | 58% | 61% | 62% | 60% | 75% | 72% | 54% | 58% | 70% | 65% | 70% | |
| 86.0% | 78% | 88% | 85% | 85% | 87% | 88% | 88% | 95% | 91% | 86% | 86% | 97% | 80% | 91% | 91% | 87% | 85% | 77% | 88% | 76% | 76% |