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 | 4th 64.7% | 2nd 65.3% | 12th 61.3% | 6th 63.7% | 5th 64.0% | 21st 53.0% | 19th 55.3% | 11th 62.0% | 12th 61.3% | 8th 63.7% | 14th 61.3% | 10th 62.7% | 15th 61.0% | 9th 63.0% | 1st 67.3% | 3rd 65.0% | 18th 56.3% | 16th 60.3% | 17th 58.0% | 20th 53.3% | 6th 63.7% | |
| 66.3% | 71% | 69% | 65% | 68% | 65% | 61% | 63% | 61% | 69% | 69% | 73% | 62% | 65% | 72% | 69% | 65% | 69% | 70% | 65% | 59% | 63% | |
| 57.6% | 62% | 65% | 63% | 68% | 63% | 43% | 48% | 63% | 62% | 57% | 49% | 51% | 51% | 50% | 67% | 65% | 46% | 63% | 53% | 59% | 62% | |
| 59.8% | 61% | 62% | 56% | 55% | 64% | 55% | 55% | 62% | 53% | 65% | 62% | 75% | 67% | 67% | 66% | 65% | 54% | 48% | 56% | 42% | 66% |