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 Bangladesh. 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 74.0% | 15th 74.0% | 20th 69.0% | 14th 75.0% | 12th 75.3% | 17th 72.5% | 6th 78.0% | 7th 77.0% | 19th 71.8% | 2nd 80.8% | 1st 82.3% | 21st 68.3% | 8th 76.5% | 9th 76.0% | 3rd 80.7% | 5th 78.3% | 11th 75.3% | 12th 75.3% | 10th 75.8% | 4th 78.8% | 18th 72.0% | |
| 58.4% | 61% | 60% | 53% | 59% | 57% | 47% | 51% | 60% | 50% | 63% | 65% | 51% | 70% | 73% | 58% | 55% | 57% | 54% | 51% | 57% | 75% | |
| 75.3% | 82% | 80% | 81% | 82% | 69% | 78% | 81% | 65% | 65% | 69% | 82% | 69% | 69% | 61% | 78% | 77% | 77% | 79% | 81% | 76% | 80% | |
| 82.0% | 78% | 77% | 75% | 78% | 87% | 80% | 89% | 86% | 83% | 91% | 89% | 74% | 78% | 74% | 92% | 88% | 74% | 84% | 78% | 89% | 78% | |
| 86.4% | 75% | 79% | 67% | 81% | 88% | 85% | 91% | 97% | 89% | 100% | 93% | 79% | 89% | 96% | 95% | 93% | 93% | 84% | 93% | 93% | 55% |