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 GD2 (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 69.3% | 12th 67.7% | 16th 67.0% | 6th 69.7% | 6th 69.7% | 19th 59.0% | 12th 67.7% | 4th 70.3% | 3rd 73.7% | 4th 70.3% | 17th 67.0% | 15th 67.3% | 10th 68.3% | 6th 69.7% | 10th 68.3% | 12th 67.7% | 20th 57.7% | 20th 57.7% | 2nd 75.3% | 17th 67.0% | 1st 81.3% | |
| 76.1% | 73% | 73% | 68% | 68% | 77% | 67% | 72% | 82% | 88% | 77% | 73% | 72% | 82% | 73% | 77% | 77% | 65% | 71% | 88% | 88% | 88% | |
| 61.3% | 68% | 61% | 68% | 74% | 65% | 57% | 64% | 58% | 64% | 61% | 61% | 58% | 46% | 58% | 57% | 61% | 43% | 54% | 67% | 54% | 88% | |
| 67.1% | 67% | 69% | 65% | 67% | 67% | 53% | 67% | 71% | 69% | 73% | 67% | 72% | 77% | 78% | 71% | 65% | 65% | 48% | 71% | 59% | 68% |