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 | 3rd 66.3% | 4th 65.3% | 8th 62.7% | 7th 63.7% | 1st 71.3% | 21st 53.7% | 20th 55.7% | 15th 59.3% | 9th 62.3% | 13th 59.7% | 10th 60.7% | 19th 57.0% | 11th 60.0% | 5th 64.7% | 2nd 67.0% | 5th 64.7% | 18th 57.3% | 11th 60.0% | 16th 58.7% | 17th 58.7% | 13th 59.7% | |
| 66.8% | 68% | 69% | 68% | 68% | 71% | 65% | 63% | 61% | 69% | 67% | 65% | 62% | 66% | 72% | 69% | 67% | 69% | 73% | 67% | 62% | 62% | |
| 58.1% | 66% | 65% | 63% | 68% | 77% | 43% | 48% | 55% | 65% | 57% | 55% | 51% | 47% | 57% | 69% | 66% | 50% | 54% | 53% | 57% | 55% | |
| 59.1% | 65% | 62% | 57% | 55% | 66% | 53% | 56% | 62% | 53% | 55% | 62% | 58% | 67% | 65% | 63% | 61% | 53% | 53% | 56% | 57% | 62% |