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 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 | 13th 66.0% | 5th 69.7% | 2nd 73.3% | 3rd 70.7% | 1st 75.3% | 20th 62.3% | 14th 65.7% | 14th 65.7% | 12th 66.3% | 16th 65.3% | 18th 64.7% | 16th 65.3% | 8th 69.3% | 7th 69.7% | 4th 70.3% | 10th 69.0% | 19th 63.0% | 11th 68.0% | 21st 61.7% | 5th 69.7% | 8th 69.3% | |
| 85.2% | 69% | 89% | 86% | 86% | 90% | 82% | 86% | 95% | 91% | 89% | 74% | 87% | 87% | 81% | 86% | 83% | 86% | 83% | 82% | 89% | 89% | |
| 50.3% | 54% | 52% | 65% | 65% | 62% | 42% | 47% | 34% | 47% | 45% | 48% | 40% | 45% | 54% | 56% | 59% | 42% | 47% | 42% | 52% | 58% | |
| 67.4% | 75% | 68% | 69% | 61% | 74% | 63% | 64% | 68% | 61% | 62% | 72% | 69% | 76% | 74% | 69% | 65% | 61% | 74% | 61% | 68% | 61% |