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 GD1 (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 | 12th 69.8% | 8th 70.3% | 15th 68.8% | 14th 69.0% | 10th 70.2% | 21st 64.3% | 18th 66.5% | 1st 72.7% | 11th 70.0% | 6th 70.7% | 9th 70.3% | 17th 67.8% | 13th 69.5% | 4th 71.3% | 2nd 72.5% | 3rd 71.5% | 19th 66.0% | 7th 70.5% | 15th 68.8% | 20th 65.5% | 5th 70.8% | |
| 51.3% | 56% | 52% | 48% | 49% | 57% | 45% | 46% | 58% | 47% | 49% | 52% | 47% | 54% | 52% | 56% | 55% | 44% | 57% | 50% | 46% | 57% | |
| 71.7% | 75% | 71% | 77% | 77% | 73% | 66% | 73% | 72% | 71% | 73% | 73% | 72% | 68% | 72% | 78% | 73% | 67% | 66% | 76% | 63% | 70% | |
| 77.0% | 79% | 80% | 81% | 81% | 72% | 66% | 71% | 79% | 83% | 79% | 81% | 74% | 76% | 74% | 79% | 81% | 78% | 80% | 71% | 75% | 77% | |
| 77.4% | 69% | 78% | 69% | 69% | 79% | 80% | 76% | 82% | 79% | 82% | 75% | 78% | 80% | 87% | 77% | 77% | 75% | 79% | 78% | 78% | 79% |