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 China. 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 | 13th 71.0% | 9th 73.0% | 12th 71.3% | 10th 72.0% | 14th 70.7% | 21st 63.3% | 7th 74.0% | 3rd 76.3% | 8th 73.3% | 2nd 76.7% | 17th 70.3% | 20th 64.7% | 17th 70.3% | 6th 74.3% | 1st 78.3% | 4th 75.0% | 19th 68.3% | 14th 70.7% | 16th 70.3% | 10th 72.0% | 4th 75.0% | |
| 79.8% | 68% | 76% | 73% | 73% | 77% | 79% | 89% | 85% | 82% | 84% | 77% | 81% | 81% | 85% | 88% | 76% | 78% | 78% | 83% | 85% | 78% | |
| 73.0% | 78% | 78% | 79% | 81% | 73% | 66% | 71% | 78% | 70% | 76% | 71% | 52% | 65% | 75% | 79% | 81% | 66% | 73% | 75% | 68% | 79% | |
| 63.0% | 67% | 65% | 62% | 62% | 62% | 45% | 62% | 66% | 68% | 70% | 63% | 61% | 65% | 63% | 68% | 68% | 61% | 61% | 53% | 63% | 68% |