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 South Africa. 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 70.5% | 8th 66.5% | 3rd 69.8% | 4th 69.3% | 7th 67.0% | 19th 57.8% | 20th 57.5% | 17th 60.0% | 13th 61.5% | 6th 67.8% | 11th 63.0% | 12th 61.8% | 13th 61.5% | 9th 63.5% | 1st 71.3% | 4th 69.3% | 17th 60.0% | 15th 61.3% | 9th 63.5% | 21st 57.3% | 15th 61.3% | |
| 60.8% | 67% | 61% | 62% | 60% | 62% | 52% | 62% | 56% | 55% | 66% | 62% | 67% | 66% | 67% | 67% | 63% | 53% | 53% | 62% | 55% | 58% | |
| 69.2% | 68% | 68% | 72% | 69% | 77% | 69% | 65% | 73% | 69% | 74% | 69% | 62% | 71% | 68% | 72% | 73% | 66% | 72% | 67% | 64% | 65% | |
| 55.7% | 63% | 59% | 66% | 69% | 62% | 48% | 48% | 40% | 51% | 64% | 50% | 50% | 42% | 50% | 69% | 68% | 55% | 51% | 60% | 51% | 54% | |
| 69.8% | 84% | 78% | 79% | 79% | 67% | 62% | 55% | 71% | 71% | 67% | 71% | 68% | 67% | 69% | 77% | 73% | 66% | 69% | 65% | 59% | 68% |