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 Kenya. 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 | 5th 69.3% | 6th 68.7% | 4th 69.7% | 2nd 70.7% | 3rd 70.3% | 21st 55.3% | 14th 63.0% | 20th 57.0% | 13th 63.3% | 8th 67.7% | 9th 67.0% | 16th 60.3% | 12th 65.3% | 18th 59.0% | 1st 72.3% | 7th 68.0% | 17th 59.3% | 10th 66.7% | 11th 65.7% | 19th 57.3% | 15th 62.7% | |
| 69.7% | 81% | 76% | 84% | 81% | 75% | 61% | 61% | 62% | 68% | 70% | 73% | 62% | 75% | 63% | 75% | 72% | 61% | 73% | 72% | 57% | 62% | |
| 57.9% | 59% | 60% | 60% | 64% | 71% | 46% | 59% | 42% | 52% | 64% | 59% | 46% | 57% | 45% | 73% | 69% | 61% | 58% | 60% | 55% | 56% | |
| 66.5% | 68% | 70% | 65% | 67% | 65% | 59% | 69% | 67% | 70% | 69% | 69% | 73% | 64% | 69% | 69% | 63% | 56% | 69% | 65% | 60% | 70% |