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 72.3% | 12th 67.7% | 14th 67.0% | 9th 69.7% | 12th 67.7% | 21st 59.0% | 18th 64.3% | 15th 66.7% | 8th 70.3% | 6th 71.7% | 17th 66.3% | 2nd 76.0% | 16th 66.3% | 7th 70.7% | 10th 69.3% | 11th 67.7% | 20th 63.0% | 19th 64.0% | 3rd 74.7% | 5th 72.0% | 1st 78.0% | |
| 77.0% | 77% | 73% | 68% | 68% | 82% | 67% | 72% | 74% | 80% | 81% | 73% | 88% | 73% | 84% | 80% | 73% | 68% | 73% | 88% | 88% | 88% | |
| 62.5% | 68% | 61% | 68% | 74% | 60% | 57% | 62% | 58% | 62% | 61% | 61% | 58% | 49% | 58% | 56% | 68% | 56% | 61% | 67% | 68% | 80% | |
| 66.8% | 72% | 69% | 65% | 67% | 61% | 53% | 59% | 68% | 69% | 73% | 65% | 82% | 77% | 70% | 72% | 62% | 65% | 58% | 69% | 60% | 66% |