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 | 3rd 72.3% | 4th 71.8% | 14th 67.8% | 12th 69.0% | 9th 70.0% | 21st 65.0% | 17th 67.5% | 1st 73.0% | 7th 71.0% | 10th 69.8% | 4th 71.8% | 19th 66.8% | 10th 69.8% | 2nd 72.8% | 7th 71.0% | 4th 71.8% | 14th 67.8% | 20th 65.3% | 14th 67.8% | 18th 67.3% | 12th 69.0% | |
| 50.2% | 56% | 52% | 48% | 49% | 57% | 47% | 51% | 58% | 47% | 49% | 58% | 43% | 50% | 52% | 49% | 55% | 44% | 54% | 43% | 49% | 44% | |
| 72.0% | 79% | 77% | 73% | 77% | 72% | 66% | 66% | 76% | 71% | 73% | 73% | 72% | 75% | 77% | 79% | 76% | 67% | 63% | 68% | 67% | 66% | |
| 77.9% | 81% | 80% | 81% | 81% | 72% | 67% | 77% | 78% | 87% | 75% | 75% | 74% | 78% | 83% | 81% | 78% | 79% | 74% | 79% | 75% | 81% | |
| 77.5% | 73% | 78% | 69% | 69% | 79% | 80% | 76% | 80% | 79% | 82% | 81% | 78% | 76% | 79% | 75% | 78% | 81% | 70% | 81% | 78% | 85% |