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 | 5th 71.8% | 10th 70.3% | 14th 68.8% | 12th 69.0% | 8th 71.5% | 20th 64.8% | 19th 66.3% | 1st 75.3% | 15th 68.3% | 6th 71.5% | 13th 69.0% | 17th 67.8% | 9th 70.5% | 3rd 72.5% | 6th 71.5% | 4th 72.0% | 18th 67.0% | 2nd 73.3% | 16th 68.0% | 21st 52.8% | 11th 69.3% | |
| 51.3% | 56% | 52% | 48% | 49% | 57% | 47% | 46% | 58% | 47% | 50% | 52% | 47% | 57% | 52% | 56% | 55% | 44% | 53% | 47% | 49% | 55% | |
| 70.1% | 79% | 71% | 77% | 77% | 73% | 66% | 72% | 77% | 71% | 77% | 73% | 72% | 73% | 77% | 73% | 75% | 67% | 73% | 73% | 10% | 67% | |
| 76.7% | 79% | 80% | 81% | 81% | 77% | 66% | 71% | 79% | 76% | 79% | 75% | 74% | 71% | 74% | 81% | 80% | 79% | 83% | 71% | 78% | 75% | |
| 78.2% | 73% | 78% | 69% | 69% | 79% | 80% | 76% | 87% | 79% | 80% | 76% | 78% | 81% | 87% | 76% | 78% | 78% | 84% | 81% | 74% | 80% |