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 70.7% | 15th 67.7% | 13th 68.3% | 8th 69.7% | 13th 68.3% | 19th 62.7% | 9th 69.3% | 16th 66.7% | 4th 73.0% | 9th 69.3% | 17th 66.3% | 5th 71.3% | 20th 60.3% | 9th 69.3% | 2nd 74.3% | 12th 68.7% | 21st 57.0% | 18th 64.3% | 3rd 73.3% | 7th 70.0% | 1st 82.3% | |
| 76.6% | 77% | 73% | 68% | 68% | 73% | 67% | 80% | 80% | 88% | 81% | 73% | 88% | 72% | 72% | 78% | 76% | 69% | 68% | 82% | 88% | 88% | |
| 62.2% | 68% | 61% | 68% | 74% | 67% | 58% | 61% | 58% | 62% | 61% | 61% | 58% | 40% | 58% | 72% | 62% | 37% | 69% | 67% | 57% | 88% | |
| 67.3% | 67% | 69% | 69% | 67% | 65% | 63% | 67% | 62% | 69% | 66% | 65% | 68% | 69% | 78% | 73% | 68% | 65% | 56% | 71% | 65% | 71% |