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 GD2 (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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 16th 71.3% | 2nd 77.0% | 9th 74.0% | 9th 74.0% | 6th 75.3% | 14th 71.7% | 5th 76.0% | 20th 68.3% | 19th 69.7% | 18th 70.0% | 14th 71.7% | 1st 78.0% | 12th 73.0% | 3rd 76.3% | 16th 71.3% | 11th 73.7% | 8th 74.3% | 7th 74.7% | 3rd 76.3% | 13th 71.7% | 21st 67.7% | |
| 80.6% | 76% | 79% | 76% | 76% | 74% | 86% | 83% | 81% | 74% | 83% | 74% | 88% | 83% | 81% | 85% | 85% | 86% | 91% | 81% | 81% | 70% | |
| 65.2% | 66% | 71% | 77% | 77% | 71% | 67% | 66% | 52% | 63% | 65% | 66% | 66% | 54% | 66% | 72% | 66% | 59% | 55% | 66% | 58% | 67% | |
| 73.6% | 72% | 81% | 69% | 69% | 81% | 62% | 79% | 72% | 72% | 62% | 75% | 80% | 82% | 82% | 57% | 70% | 78% | 78% | 82% | 76% | 66% |