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 | 15th 77.0% | 6th 81.5% | 2nd 84.7% | 3rd 84.3% | 4th 82.8% | 13th 77.8% | 1st 84.8% | 21st 72.5% | 12th 78.0% | 5th 81.8% | 15th 77.0% | 7th 81.0% | 19th 76.8% | 8th 80.3% | 11th 78.5% | 9th 79.3% | 15th 77.0% | 18th 76.8% | 14th 77.3% | 20th 74.3% | 9th 79.3% | |
| 73.0% | 75% | 75% | 74% | 74% | 71% | 71% | 81% | 72% | 79% | 78% | 75% | 75% | 69% | 75% | 71% | 66% | 70% | 70% | 75% | 62% | 74% | |
| 85.2% | 84% | 90% | 100% | 89% | 89% | 81% | 90% | 76% | 82% | 81% | 90% | 81% | 82% | 90% | 86% | 87% | 82% | 82% | 81% | 78% | 89% | |
| 75.0% | 75% | 85% | 91% | 100% | 79% | 84% | 75% | 55% | 73% | 75% | 65% | 75% | 63% | 75% | 75% | 81% | 69% | 80% | 75% | 64% | 61% | |
| 83.4% | 74% | 76% | 74% | 74% | 92% | 75% | 93% | 87% | 78% | 93% | 78% | 93% | 93% | 81% | 82% | 83% | 87% | 75% | 78% | 93% | 93% |