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 | 4th 81.0% | 1st 83.5% | 10th 78.5% | 15th 76.5% | 3rd 81.5% | 21st 73.0% | 7th 79.5% | 8th 79.0% | 12th 77.8% | 20th 74.0% | 5th 80.5% | 14th 76.8% | 17th 76.3% | 19th 74.5% | 15th 76.5% | 9th 78.8% | 13th 77.0% | 18th 75.3% | 2nd 81.8% | 6th 80.3% | 11th 77.8% | |
| 79.0% | 81% | 82% | 81% | 71% | 77% | 72% | 82% | 78% | 81% | 81% | 75% | 78% | 75% | 81% | 82% | 86% | 74% | 72% | 88% | 82% | 80% | |
| 86.0% | 86% | 100% | 90% | 86% | 86% | 81% | 95% | 94% | 83% | 76% | 90% | 86% | 86% | 81% | 81% | 82% | 82% | 82% | 86% | 90% | 82% | |
| 67.7% | 65% | 71% | 65% | 75% | 71% | 61% | 65% | 66% | 65% | 58% | 85% | 65% | 66% | 58% | 65% | 66% | 78% | 73% | 61% | 71% | 71% | |
| 79.7% | 92% | 81% | 78% | 74% | 92% | 78% | 76% | 78% | 82% | 81% | 72% | 78% | 78% | 78% | 78% | 81% | 74% | 74% | 92% | 78% | 78% |