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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 10th 75.8% | 14th 74.8% | 20th 69.0% | 13th 75.0% | 11th 75.5% | 17th 73.3% | 5th 79.8% | 17th 73.3% | 19th 70.5% | 2nd 81.3% | 7th 77.3% | 20th 69.0% | 7th 77.3% | 9th 76.0% | 1st 83.5% | 16th 73.8% | 11th 75.5% | 4th 80.5% | 15th 74.3% | 3rd 80.8% | 5th 79.8% | |
| 59.9% | 65% | 60% | 53% | 59% | 51% | 47% | 51% | 60% | 50% | 58% | 65% | 44% | 65% | 73% | 67% | 57% | 59% | 76% | 51% | 76% | 70% | |
| 74.3% | 82% | 80% | 81% | 82% | 72% | 78% | 81% | 63% | 63% | 76% | 82% | 69% | 69% | 61% | 77% | 75% | 79% | 67% | 73% | 75% | 76% | |
| 81.8% | 75% | 80% | 75% | 78% | 83% | 83% | 89% | 83% | 80% | 91% | 75% | 74% | 83% | 74% | 90% | 87% | 83% | 92% | 80% | 83% | 80% | |
| 87.9% | 81% | 79% | 67% | 81% | 96% | 85% | 98% | 87% | 89% | 100% | 87% | 89% | 92% | 96% | 100% | 76% | 81% | 87% | 93% | 89% | 93% |