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 | 3rd 81.0% | 7th 78.5% | 14th 76.5% | 10th 77.5% | 1st 81.5% | 21st 73.0% | 5th 79.0% | 9th 77.8% | 20th 74.0% | 13th 76.8% | 16th 76.3% | 19th 74.5% | 14th 76.5% | 6th 78.8% | 11th 77.0% | 1st 81.5% | 11th 77.0% | 17th 75.3% | 4th 80.3% | 8th 77.8% | 18th 75.0% | |
| 78.2% | 81% | 81% | 71% | 71% | 77% | 72% | 78% | 81% | 81% | 78% | 75% | 81% | 82% | 86% | 79% | 81% | 74% | 72% | 82% | 80% | 80% | |
| 84.8% | 86% | 90% | 86% | 94% | 86% | 81% | 94% | 83% | 76% | 86% | 86% | 81% | 81% | 82% | 89% | 82% | 82% | 82% | 90% | 82% | 82% | |
| 67.7% | 65% | 65% | 75% | 71% | 71% | 61% | 66% | 65% | 58% | 65% | 66% | 58% | 65% | 66% | 66% | 81% | 78% | 73% | 71% | 71% | 64% | |
| 78.9% | 92% | 78% | 74% | 74% | 92% | 78% | 78% | 82% | 81% | 78% | 78% | 78% | 78% | 81% | 74% | 82% | 74% | 74% | 78% | 78% | 74% |