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 | 20th 61.3% | 1st 70.7% | 6th 68.3% | 2nd 69.7% | 5th 69.3% | 21st 60.0% | 14th 65.7% | 18th 64.0% | 15th 65.0% | 13th 66.0% | 10th 67.3% | 17th 64.3% | 12th 66.3% | 7th 68.0% | 2nd 69.7% | 9th 67.7% | 16th 64.7% | 7th 68.0% | 19th 62.7% | 11th 66.3% | 2nd 69.7% | |
| 85.3% | 72% | 89% | 86% | 86% | 90% | 82% | 86% | 89% | 87% | 89% | 81% | 87% | 82% | 87% | 90% | 83% | 87% | 81% | 87% | 80% | 90% | |
| 46.9% | 45% | 52% | 65% | 62% | 49% | 36% | 47% | 34% | 47% | 39% | 44% | 40% | 40% | 40% | 54% | 55% | 44% | 47% | 40% | 54% | 50% | |
| 67.1% | 67% | 71% | 54% | 61% | 69% | 62% | 64% | 69% | 61% | 70% | 77% | 66% | 77% | 77% | 65% | 65% | 63% | 76% | 61% | 65% | 69% |