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 | 3rd 82.0% | 7th 77.3% | 9th 76.8% | 8th 77.0% | 17th 71.0% | 21st 65.8% | 20th 69.8% | 19th 70.2% | 15th 74.3% | 4th 81.0% | 12th 75.5% | 17th 71.0% | 13th 75.3% | 16th 73.5% | 9th 76.8% | 6th 77.8% | 11th 75.8% | 5th 78.3% | 2nd 82.5% | 14th 74.5% | 1st 86.0% | |
| 69.6% | 73% | 70% | 60% | 69% | 68% | 54% | 65% | 72% | 66% | 73% | 77% | 70% | 73% | 70% | 74% | 74% | 70% | 68% | 75% | 64% | 77% | |
| 79.0% | 85% | 77% | 84% | 84% | 77% | 71% | 80% | 77% | 77% | 85% | 82% | 79% | 85% | 77% | 85% | 80% | 72% | 73% | 85% | 68% | 77% | |
| 69.6% | 74% | 75% | 78% | 71% | 72% | 59% | 51% | 52% | 74% | 74% | 59% | 57% | 60% | 64% | 65% | 73% | 71% | 77% | 78% | 82% | 95% | |
| 85.0% | 96% | 87% | 85% | 84% | 67% | 79% | 83% | 80% | 80% | 92% | 84% | 78% | 83% | 83% | 83% | 84% | 90% | 95% | 92% | 84% | 95% |