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 | 7th 77.3% | 11th 74.8% | 19th 69.5% | 10th 75.0% | 17th 72.5% | 15th 73.3% | 3rd 79.8% | 13th 74.3% | 16th 73.3% | 2nd 80.0% | 4th 79.5% | 20th 65.0% | 8th 76.0% | 14th 74.0% | 5th 79.5% | 6th 77.3% | 18th 70.0% | 21st 61.3% | 9th 75.3% | 11th 74.8% | 1st 82.5% | |
| 56.8% | 65% | 60% | 53% | 59% | 51% | 47% | 51% | 60% | 51% | 63% | 65% | 44% | 70% | 62% | 58% | 56% | 44% | 50% | 55% | 52% | 76% | |
| 73.7% | 82% | 80% | 81% | 82% | 61% | 78% | 81% | 69% | 62% | 66% | 82% | 64% | 76% | 64% | 78% | 76% | 76% | 61% | 73% | 76% | 79% | |
| 78.9% | 75% | 80% | 75% | 78% | 87% | 83% | 89% | 79% | 80% | 91% | 78% | 74% | 69% | 74% | 87% | 84% | 68% | 64% | 80% | 79% | 82% | |
| 88.7% | 87% | 79% | 69% | 81% | 91% | 85% | 98% | 89% | 100% | 100% | 93% | 78% | 89% | 96% | 95% | 93% | 92% | 70% | 93% | 92% | 93% |