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 | 13th 76.8% | 13th 76.8% | 8th 77.5% | 10th 77.3% | 3rd 79.0% | 19th 74.0% | 1st 80.5% | 12th 77.0% | 15th 76.0% | 7th 77.5% | 2nd 79.5% | 17th 75.8% | 16th 76.0% | 9th 77.3% | 10th 77.3% | 4th 78.5% | 18th 74.5% | 19th 74.0% | 5th 78.5% | 6th 77.8% | 21st 70.3% | |
| 76.4% | 81% | 74% | 71% | 71% | 77% | 72% | 78% | 81% | 78% | 75% | 73% | 82% | 80% | 71% | 82% | 74% | 70% | 75% | 80% | 83% | ||
| 85.6% | 80% | 90% | 86% | 94% | 86% | 81% | 100% | 81% | 76% | 86% | 94% | 90% | 86% | 82% | 89% | 80% | 81% | 82% | 90% | 82% | 82% | |
| 67.2% | 65% | 65% | 75% | 66% | 71% | 65% | 66% | 65% | 65% | 65% | 71% | 59% | 58% | 66% | 71% | 71% | 65% | 69% | 71% | 71% | 71% | |
| 77.8% | 81% | 78% | 78% | 78% | 82% | 78% | 78% | 81% | 87% | 81% | 78% | 81% | 78% | 81% | 78% | 81% | 78% | 75% | 78% | 78% | 45% |