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 | 2nd 72.0% | 17th 64.0% | 13th 64.7% | 7th 67.3% | 10th 65.0% | 18th 63.3% | 10th 65.0% | 5th 68.3% | 14th 64.3% | 10th 65.0% | 14th 64.3% | 9th 66.0% | 19th 58.7% | 6th 68.0% | 4th 69.3% | 1st 72.3% | 8th 66.3% | 20th 56.7% | 3rd 70.7% | 21st 56.3% | 16th 64.3% | |
| 72.5% | 81% | 68% | 74% | 74% | 70% | 70% | 81% | 81% | 81% | 81% | 68% | 68% | 58% | 74% | 74% | 88% | 74% | 56% | 78% | 65% | 58% | |
| 49.0% | 58% | 51% | 51% | 51% | 51% | 51% | 44% | 44% | 42% | 44% | 51% | 47% | 44% | 48% | 58% | 60% | 51% | 44% | 60% | 31% | 47% | |
| 74.6% | 77% | 73% | 69% | 77% | 74% | 69% | 70% | 80% | 70% | 70% | 74% | 83% | 74% | 82% | 76% | 69% | 74% | 70% | 74% | 73% | 88% |