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 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 | 12th 77.0% | 13th 76.8% | 16th 76.5% | 16th 76.5% | 6th 79.0% | 21st 72.0% | 1st 80.5% | 11th 77.3% | 20th 74.0% | 4th 79.3% | 3rd 79.5% | 18th 75.8% | 9th 78.3% | 7th 78.8% | 4th 79.3% | 9th 78.3% | 2nd 80.0% | 15th 76.8% | 8th 78.5% | 13th 76.8% | 19th 75.0% | |
| 77.8% | 81% | 74% | 71% | 71% | 77% | 72% | 78% | 81% | 81% | 85% | 75% | 80% | 88% | 82% | 78% | 75% | 80% | 69% | 75% | 80% | 80% | |
| 85.6% | 80% | 90% | 86% | 86% | 86% | 81% | 100% | 81% | 76% | 86% | 94% | 90% | 86% | 86% | 86% | 86% | 82% | 82% | 90% | 82% | 82% | |
| 67.6% | 65% | 65% | 75% | 75% | 71% | 61% | 66% | 65% | 61% | 65% | 71% | 59% | 61% | 66% | 71% | 74% | 58% | 73% | 71% | 71% | 75% | |
| 78.7% | 82% | 78% | 74% | 74% | 82% | 74% | 78% | 82% | 78% | 81% | 78% | 74% | 78% | 81% | 82% | 78% | 100% | 83% | 78% | 74% | 63% |