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 | 18th 67.0% | 7th 72.3% | 15th 68.0% | 15th 68.0% | 4th 73.0% | 9th 71.0% | 8th 71.3% | 17th 67.7% | 11th 70.3% | 20th 65.7% | 5th 73.0% | 12th 70.0% | 10th 70.7% | 1st 77.7% | 19th 66.7% | 13th 69.3% | 2nd 76.3% | 3rd 73.7% | 14th 69.0% | 5th 73.0% | 21st 61.3% | |
| 72.6% | 67% | 75% | 76% | 76% | 74% | 81% | 76% | 74% | 74% | 74% | 74% | 58% | 74% | 80% | 70% | 75% | 85% | 73% | 60% | 71% | 58% | |
| 64.0% | 65% | 71% | 66% | 66% | 67% | 67% | 63% | 57% | 60% | 55% | 66% | 66% | 54% | 65% | 69% | 65% | 65% | 66% | 71% | 66% | 55% | |
| 74.0% | 69% | 71% | 62% | 62% | 78% | 65% | 75% | 72% | 77% | 68% | 79% | 86% | 84% | 88% | 61% | 68% | 79% | 82% | 76% | 82% | 71% |