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 GD2 (https://github.com/collect-intel/global-dialogues)
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 65.0% | 6th 63.3% | 4th 65.0% | 1st 72.7% | 13th 50.7% | 12th 53.3% | 9th 58.3% | 8th 61.7% | 3rd 65.3% | 10th 55.7% | 7th 62.3% | 11th 55.3% | 2nd 70.3% | |
| 73.5% | 78% | 80% | 80% | 80% | 64% | 60% | 71% | 71% | 80% | 71% | 70% | 71% | 80% | |
| 57.5% | 63% | 63% | 68% | 80% | 43% | 53% | 53% | 56% | 53% | 46% | 53% | 48% | 68% | |
| 53.4% | 54% | 47% | 47% | 58% | 45% | 47% | 51% | 58% | 63% | 50% | 64% | 47% | 63% |