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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 6th 73.0% | 7th 71.0% | 4th 73.3% | 3rd 75.3% | 2nd 75.7% | 20th 62.0% | 14th 67.3% | 19th 63.3% | 10th 69.7% | 8th 70.7% | 8th 70.7% | 10th 69.7% | 20th 62.0% | 15th 66.7% | 1st 76.3% | 4th 73.3% | 13th 67.7% | 12th 68.3% | 18th 64.3% | 17th 64.7% | 15th 66.7% | |
| 74.6% | 81% | 77% | 84% | 84% | 84% | 77% | 62% | 68% | 73% | 73% | 83% | 70% | 64% | 73% | 84% | 77% | 76% | 76% | 62% | 77% | 62% | |
| 60.1% | 61% | 64% | 64% | 70% | 70% | 45% | 61% | 45% | 64% | 66% | 57% | 64% | 50% | 50% | 70% | 71% | 55% | 52% | 64% | 53% | 66% | |
| 72.7% | 77% | 72% | 72% | 72% | 73% | 64% | 79% | 77% | 72% | 73% | 72% | 75% | 72% | 77% | 75% | 72% | 72% | 77% | 67% | 64% | 72% |