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 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 67.3% | 6th 65.0% | 9th 62.7% | 6th 65.0% | 8th 64.0% | 20th 51.7% | 19th 53.3% | 18th 54.7% | 12th 59.3% | 10th 61.7% | 5th 65.3% | 13th 59.3% | 14th 58.3% | 4th 65.7% | 3rd 66.3% | 1st 70.7% | 17th 56.0% | 11th 59.7% | 14th 58.3% | 21st 51.3% | 16th 57.0% | |
| 72.1% | 80% | 78% | 78% | 80% | 71% | 64% | 60% | 71% | 71% | 71% | 80% | 71% | 64% | 80% | 78% | 78% | 64% | 72% | 71% | 67% | 66% | |
| 55.6% | 65% | 63% | 63% | 68% | 63% | 46% | 53% | 46% | 53% | 56% | 53% | 46% | 53% | 53% | 63% | 71% | 51% | 56% | 46% | 40% | 60% | |
| 54.0% | 57% | 54% | 47% | 47% | 58% | 45% | 47% | 47% | 54% | 58% | 63% | 61% | 58% | 64% | 58% | 63% | 53% | 51% | 58% | 47% | 45% |