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 Russian Federation. 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 Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 70.3% | 3rd 71.7% | 4th 70.7% | 2nd 72.7% | 12th 62.0% | 9th 65.3% | 11th 64.7% | 8th 66.0% | 7th 67.3% | 10th 65.0% | 6th 68.0% | 13th 61.0% | 1st 73.3% | |
| 86.5% | 89% | 86% | 86% | 95% | 82% | 88% | 86% | 89% | 81% | 86% | 87% | 82% | 87% | |
| 49.1% | 50% | 65% | 65% | 49% | 42% | 44% | 47% | 47% | 49% | 40% | 40% | 40% | 60% | |
| 67.1% | 72% | 64% | 61% | 74% | 62% | 64% | 61% | 62% | 72% | 69% | 77% | 61% | 73% |