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 Philippines. 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 | 5th 72.7% | 8th 71.0% | 3rd 74.0% | 2nd 75.3% | 1st 77.7% | 20th 59.0% | 15th 67.3% | 17th 65.0% | 9th 70.7% | 7th 71.3% | 10th 70.3% | 12th 69.3% | 19th 63.0% | 6th 72.0% | 4th 73.7% | 13th 69.0% | 14th 68.7% | 11th 69.7% | 18th 63.3% | 21st 57.7% | 16th 65.3% | |
| 72.8% | 83% | 77% | 84% | 84% | 84% | 77% | 62% | 68% | 73% | 75% | 76% | 70% | 64% | 73% | 77% | 67% | 73% | 74% | 62% | 64% | 62% | |
| 61.3% | 61% | 64% | 66% | 70% | 77% | 40% | 61% | 50% | 64% | 66% | 62% | 61% | 55% | 64% | 70% | 67% | 62% | 60% | 64% | 43% | 61% | |
| 72.4% | 74% | 72% | 72% | 72% | 72% | 60% | 79% | 77% | 75% | 73% | 73% | 77% | 70% | 79% | 74% | 73% | 71% | 75% | 64% | 66% | 73% |