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 | 14th 77.0% | 15th 76.8% | 18th 76.5% | 7th 78.5% | 1st 81.5% | 21st 71.5% | 11th 77.3% | 11th 77.3% | 19th 75.5% | 15th 76.8% | 4th 79.3% | 5th 79.0% | 2nd 80.0% | 10th 77.5% | 6th 78.5% | 3rd 79.8% | 11th 77.3% | 15th 76.8% | 7th 78.5% | 20th 73.5% | 9th 77.8% | |
| 78.2% | 81% | 74% | 71% | 71% | 77% | 72% | 71% | 81% | 74% | 78% | 82% | 81% | 88% | 82% | 82% | 78% | 75% | 88% | 75% | 80% | 82% | |
| 85.4% | 80% | 90% | 86% | 94% | 86% | 81% | 94% | 81% | 76% | 86% | 86% | 90% | 86% | 81% | 86% | 88% | 82% | 86% | 90% | 82% | 83% | |
| 66.0% | 65% | 65% | 75% | 75% | 71% | 61% | 66% | 65% | 65% | 65% | 71% | 58% | 65% | 66% | 65% | 75% | 65% | 55% | 71% | 58% | 64% | |
| 80.1% | 82% | 78% | 74% | 74% | 92% | 72% | 78% | 82% | 87% | 78% | 78% | 87% | 81% | 81% | 81% | 78% | 87% | 78% | 78% | 74% | 82% |