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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 67.7% | 5th 65.0% | 8th 63.3% | 5th 65.0% | 7th 63.7% | 21st 51.7% | 19th 53.3% | 15th 59.3% | 11th 61.7% | 10th 61.7% | 4th 65.3% | 17th 58.0% | 16th 58.3% | 3rd 65.7% | 1st 71.7% | 12th 61.3% | 18th 56.3% | 9th 62.7% | 13th 60.3% | 19th 53.3% | 14th 59.3% | |
| 72.4% | 81% | 78% | 80% | 80% | 70% | 64% | 60% | 71% | 71% | 71% | 80% | 71% | 64% | 80% | 80% | 73% | 72% | 77% | 71% | 63% | 64% | |
| 56.8% | 65% | 63% | 63% | 68% | 63% | 46% | 53% | 43% | 63% | 56% | 53% | 46% | 53% | 53% | 70% | 60% | 51% | 53% | 63% | 51% | 56% | |
| 54.3% | 57% | 54% | 47% | 47% | 58% | 45% | 47% | 64% | 51% | 58% | 63% | 57% | 58% | 64% | 65% | 51% | 46% | 58% | 47% | 46% | 58% |