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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 6th 67.0% | 7th 66.5% | 1st 70.5% | 4th 67.5% | 3rd 69.3% | 20th 57.5% | 18th 58.3% | 11th 64.0% | 16th 62.0% | 9th 64.5% | 5th 67.3% | 13th 63.3% | 17th 62.0% | 9th 64.5% | 2nd 69.5% | 8th 65.8% | 18th 58.3% | 12th 63.5% | 15th 62.2% | 21st 55.3% | 14th 63.0% | |
| 60.8% | 64% | 61% | 62% | 60% | 66% | 55% | 62% | 56% | 56% | 66% | 63% | 67% | 62% | 67% | 67% | 59% | 53% | 60% | 57% | 53% | 61% | |
| 70.0% | 67% | 68% | 72% | 69% | 82% | 65% | 65% | 77% | 68% | 69% | 77% | 72% | 73% | 72% | 70% | 70% | 66% | 73% | 67% | 58% | 69% | |
| 54.9% | 58% | 59% | 69% | 62% | 62% | 48% | 51% | 58% | 51% | 56% | 50% | 46% | 45% | 50% | 62% | 60% | 48% | 48% | 60% | 51% | 58% | |
| 69.9% | 79% | 78% | 79% | 79% | 67% | 62% | 55% | 65% | 73% | 67% | 79% | 68% | 68% | 69% | 79% | 74% | 66% | 73% | 65% | 59% | 64% |