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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 13th 76.0% | 1st 81.7% | 11th 76.8% | 10th 77.5% | 4th 79.0% | 20th 72.0% | 9th 77.8% | 3rd 79.0% | 17th 74.8% | 13th 76.0% | 2nd 81.5% | 5th 78.5% | 7th 78.3% | 16th 76.0% | 8th 78.0% | 12th 76.3% | 21st 70.8% | 19th 73.0% | 13th 76.0% | 5th 78.5% | 18th 74.0% | |
| 77.8% | 81% | 82% | 74% | 71% | 77% | 72% | 83% | 78% | 81% | 82% | 80% | 85% | 82% | 73% | 88% | 76% | 78% | 70% | 75% | 75% | 71% | |
| 85.6% | 80% | 100% | 90% | 86% | 86% | 81% | 89% | 94% | 72% | 76% | 92% | 86% | 87% | 90% | 81% | 82% | 82% | 87% | 86% | 90% | 80% | |
| 65.6% | 65% | 71% | 65% | 75% | 71% | 61% | 63% | 66% | 65% | 65% | 81% | 65% | 66% | 59% | 65% | 66% | 41% | 61% | 65% | 71% | 71% | |
| 77.9% | 78% | 74% | 78% | 78% | 82% | 74% | 76% | 78% | 81% | 81% | 73% | 78% | 78% | 82% | 78% | 81% | 82% | 74% | 78% | 78% | 74% |