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% | 14th 76.8% | 16th 76.5% | 3rd 80.3% | 7th 79.0% | 21st 71.5% | 2nd 80.5% | 12th 77.0% | 18th 75.5% | 10th 78.5% | 5th 80.0% | 17th 75.8% | 6th 79.3% | 11th 77.3% | 14th 76.8% | 1st 81.8% | 9th 78.8% | 20th 73.3% | 3rd 80.3% | 19th 75.5% | 7th 79.0% | |
| 77.0% | 81% | 74% | 71% | 71% | 77% | 72% | 78% | 81% | 74% | 85% | 81% | 73% | 88% | 76% | 78% | 81% | 68% | 70% | 82% | 75% | 80% | |
| 86.5% | 80% | 90% | 86% | 94% | 86% | 81% | 100% | 81% | 76% | 86% | 90% | 90% | 86% | 86% | 89% | 90% | 89% | 82% | 90% | 82% | 82% | |
| 68.0% | 65% | 65% | 75% | 75% | 71% | 61% | 66% | 65% | 65% | 65% | 71% | 59% | 65% | 66% | 66% | 75% | 71% | 67% | 71% | 71% | 72% | |
| 79.1% | 82% | 78% | 74% | 81% | 82% | 72% | 78% | 81% | 87% | 78% | 78% | 81% | 78% | 81% | 74% | 81% | 87% | 74% | 78% | 74% | 82% |