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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 6th 64.0% | 2nd 65.3% | 12th 61.3% | 8th 63.7% | 3rd 65.0% | 21st 52.3% | 18th 57.3% | 20th 54.3% | 6th 64.0% | 9th 62.7% | 10th 62.0% | 19th 57.0% | 17th 58.3% | 5th 64.7% | 3rd 65.0% | 1st 66.0% | 10th 62.0% | 13th 60.7% | 15th 58.7% | 16th 58.7% | 14th 60.3% | |
| 65.9% | 65% | 69% | 65% | 68% | 65% | 61% | 63% | 61% | 69% | 69% | 73% | 62% | 60% | 72% | 65% | 67% | 62% | 70% | 67% | 63% | 68% | |
| 56.8% | 62% | 65% | 63% | 68% | 63% | 43% | 48% | 40% | 58% | 58% | 51% | 51% | 48% | 57% | 67% | 70% | 59% | 50% | 53% | 57% | 62% | |
| 60.6% | 65% | 62% | 56% | 55% | 67% | 53% | 61% | 62% | 65% | 61% | 62% | 58% | 67% | 65% | 63% | 61% | 65% | 62% | 56% | 56% | 51% |