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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 69.7% | 14th 64.0% | 5th 68.0% | 7th 67.3% | 2nd 69.7% | 15th 63.3% | 4th 69.3% | 8th 66.3% | 16th 63.0% | 17th 62.7% | 11th 65.3% | 13th 64.3% | 12th 64.7% | 5th 68.0% | 8th 66.3% | 8th 66.3% | 20th 57.7% | 18th 60.3% | 1st 71.7% | 21st 57.3% | 19th 60.3% | |
| 73.0% | 74% | 68% | 74% | 74% | 84% | 70% | 87% | 81% | 81% | 74% | 68% | 68% | 81% | 74% | 72% | 68% | 68% | 65% | 78% | 65% | 58% | |
| 50.3% | 58% | 51% | 61% | 51% | 51% | 51% | 51% | 48% | 41% | 44% | 51% | 47% | 44% | 48% | 56% | 58% | 44% | 47% | 60% | 44% | 51% | |
| 71.8% | 77% | 73% | 69% | 77% | 74% | 69% | 70% | 70% | 67% | 70% | 77% | 78% | 69% | 82% | 71% | 73% | 61% | 69% | 77% | 63% | 72% |