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 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 | 7th 74.5% | 2nd 76.3% | 9th 74.0% | 6th 74.5% | 3rd 75.3% | 19th 68.3% | 13th 72.5% | 17th 68.8% | 11th 73.5% | 8th 74.3% | 5th 74.8% | 4th 74.8% | 14th 72.0% | 12th 73.3% | 1st 77.5% | 10th 73.8% | 15th 71.7% | 20th 66.5% | 16th 71.5% | 21st 65.0% | 18th 68.5% | |
| 82.9% | 84% | 87% | 78% | 77% | 85% | 77% | 85% | 88% | 84% | 85% | 88% | 89% | 85% | 93% | 90% | 79% | 71% | 79% | 76% | 78% | 83% | |
| 64.6% | 69% | 67% | 66% | 66% | 68% | 64% | 73% | 50% | 60% | 68% | 69% | 68% | 68% | 62% | 64% | 68% | 71% | 56% | 64% | 58% | 57% | |
| 56.4% | 59% | 61% | 62% | 65% | 61% | 49% | 47% | 49% | 62% | 56% | 49% | 59% | 52% | 50% | 69% | 59% | 61% | 45% | 61% | 52% | 56% | |
| 85.9% | 86% | 90% | 90% | 90% | 87% | 83% | 85% | 88% | 88% | 88% | 93% | 83% | 83% | 88% | 87% | 89% | 84% | 86% | 85% | 72% | 78% |