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 | 9th 75.8% | 12th 74.8% | 20th 69.5% | 10th 75.0% | 8th 76.8% | 17th 72.0% | 4th 79.8% | 18th 70.0% | 19th 69.8% | 3rd 80.0% | 5th 79.5% | 21st 66.3% | 6th 77.3% | 6th 77.3% | 1st 82.5% | 10th 75.0% | 15th 73.0% | 16th 72.8% | 13th 74.5% | 14th 74.3% | 2nd 81.8% | |
| 57.0% | 65% | 60% | 53% | 59% | 51% | 47% | 51% | 53% | 50% | 64% | 65% | 44% | 63% | 67% | 67% | 58% | 57% | 44% | 54% | 50% | 76% | |
| 75.8% | 82% | 80% | 81% | 82% | 81% | 78% | 81% | 69% | 62% | 76% | 82% | 69% | 69% | 67% | 79% | 77% | 73% | 79% | 73% | 71% | 80% | |
| 81.2% | 75% | 80% | 75% | 78% | 87% | 78% | 89% | 79% | 78% | 91% | 78% | 74% | 85% | 79% | 91% | 83% | 83% | 76% | 78% | 87% | 82% | |
| 86.4% | 81% | 79% | 69% | 81% | 88% | 85% | 98% | 79% | 89% | 89% | 93% | 78% | 92% | 96% | 93% | 82% | 79% | 92% | 93% | 89% | 89% |