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 | 17th 64.0% | 1st 70.7% | 6th 68.3% | 1st 70.7% | 4th 69.3% | 19th 62.3% | 12th 65.7% | 10th 67.0% | 8th 67.3% | 15th 65.0% | 8th 67.3% | 15th 65.0% | 4th 69.3% | 11th 66.0% | 7th 68.0% | 1st 70.7% | 18th 63.3% | 20th 61.0% | 20th 61.0% | 12th 65.7% | 14th 65.3% | |
| 84.4% | 69% | 89% | 86% | 86% | 86% | 82% | 86% | 100% | 86% | 89% | 81% | 86% | 87% | 81% | 83% | 85% | 78% | 78% | 82% | 81% | 91% | |
| 47.8% | 51% | 51% | 65% | 65% | 49% | 42% | 44% | 33% | 47% | 43% | 49% | 40% | 45% | 40% | 53% | 62% | 51% | 42% | 40% | 58% | 34% | |
| 66.8% | 72% | 72% | 54% | 61% | 73% | 63% | 67% | 68% | 69% | 63% | 72% | 69% | 76% | 77% | 68% | 65% | 61% | 63% | 61% | 58% | 71% |