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 Brazil. 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 | 5th 79.0% | 3rd 80.7% | 8th 76.0% | 7th 76.3% | 6th 78.7% | 21st 62.0% | 14th 72.3% | 2nd 82.0% | 10th 75.0% | 9th 75.7% | 11th 74.3% | 18th 70.3% | 16th 71.0% | 12th 73.0% | 1st 82.3% | 3rd 80.7% | 19th 69.0% | 14th 72.3% | 13th 72.7% | 20th 66.0% | 16th 71.0% | |
| 88.6% | 96% | 96% | 96% | 94% | 96% | 81% | 80% | 96% | 88% | 88% | 90% | 81% | 79% | 87% | 96% | 93% | 91% | 94% | 88% | 75% | 75% | |
| 59.0% | 61% | 63% | 63% | 68% | 64% | 51% | 59% | 63% | 62% | 61% | 55% | 50% | 58% | 52% | 73% | 65% | 52% | 45% | 61% | 52% | 61% | |
| 75.3% | 80% | 83% | 69% | 67% | 76% | 54% | 78% | 87% | 75% | 78% | 78% | 80% | 76% | 80% | 78% | 84% | 64% | 78% | 69% | 71% | 77% |