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 | 14th 74.3% | 6th 78.8% | 20th 69.5% | 11th 75.0% | 12th 74.5% | 17th 73.3% | 7th 78.3% | 15th 74.0% | 18th 73.0% | 1st 80.3% | 2nd 80.0% | 21st 66.3% | 10th 75.8% | 8th 76.8% | 4th 79.5% | 5th 79.0% | 12th 74.5% | 19th 71.2% | 9th 76.3% | 15th 74.0% | 2nd 80.0% | |
| 58.4% | 65% | 61% | 53% | 59% | 51% | 47% | 51% | 60% | 50% | 61% | 69% | 44% | 63% | 62% | 69% | 61% | 57% | 54% | 57% | 57% | 75% | |
| 74.3% | 82% | 80% | 81% | 82% | 72% | 78% | 81% | 64% | 63% | 69% | 81% | 69% | 76% | 70% | 78% | 69% | 72% | 63% | 81% | 71% | 79% | |
| 79.8% | 75% | 80% | 75% | 78% | 87% | 83% | 83% | 85% | 79% | 91% | 77% | 74% | 72% | 79% | 84% | 86% | 73% | 84% | 74% | 79% | 77% | |
| 89.2% | 75% | 94% | 69% | 81% | 88% | 85% | 98% | 87% | 100% | 100% | 93% | 78% | 92% | 96% | 87% | 100% | 96% | 84% | 93% | 89% | 89% |