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 | 3rd 81.3% | 14th 74.0% | 19th 69.0% | 12th 75.0% | 10th 75.5% | 17th 73.3% | 5th 79.8% | 11th 75.3% | 15th 73.5% | 4th 81.0% | 1st 82.8% | 21st 66.0% | 8th 77.3% | 9th 75.8% | 2nd 82.3% | 7th 77.7% | 13th 74.8% | 18th 69.8% | 16th 73.5% | 20th 68.3% | 6th 78.8% | |
| 58.3% | 65% | 60% | 53% | 59% | 51% | 47% | 51% | 60% | 51% | 64% | 69% | 37% | 63% | 67% | 67% | 58% | 57% | 56% | 53% | 56% | 80% | |
| 73.5% | 82% | 80% | 81% | 82% | 73% | 78% | 81% | 65% | 65% | 69% | 82% | 69% | 69% | 61% | 81% | 74% | 69% | 69% | 73% | 64% | 76% | |
| 82.5% | 91% | 77% | 75% | 78% | 87% | 83% | 89% | 79% | 78% | 91% | 87% | 80% | 85% | 79% | 83% | 84% | 84% | 84% | 75% | 80% | ||
| 88.2% | 87% | 79% | 67% | 81% | 91% | 85% | 98% | 97% | 100% | 100% | 93% | 78% | 92% | 96% | 98% | 95% | 89% | 70% | 93% | 85% | 79% |