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 Australia. Source: Global Dialogues GD2 (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 | 10th 71.7% | 4th 75.7% | 7th 74.0% | 7th 74.0% | 9th 73.0% | 11th 71.7% | 3rd 76.0% | 21st 67.0% | 20th 67.3% | 15th 70.3% | 14th 71.3% | 1st 77.7% | 4th 75.7% | 15th 70.3% | 17th 69.0% | 19th 68.0% | 6th 75.3% | 11th 71.7% | 2nd 77.0% | 11th 71.7% | 17th 69.0% | |
| 80.3% | 77% | 79% | 76% | 76% | 78% | 86% | 83% | 81% | 74% | 83% | 74% | 88% | 85% | 71% | 76% | 81% | 85% | 85% | 83% | 88% | 77% | |
| 64.3% | 66% | 67% | 77% | 77% | 66% | 67% | 66% | 48% | 59% | 66% | 58% | 66% | 60% | 58% | 65% | 66% | 63% | 64% | 66% | 59% | 66% | |
| 72.2% | 72% | 81% | 69% | 69% | 75% | 62% | 79% | 72% | 69% | 62% | 82% | 79% | 82% | 82% | 66% | 57% | 78% | 66% | 82% | 68% | 64% |