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 | 5th 68.0% | 16th 64.0% | 13th 64.7% | 6th 67.3% | 2nd 71.0% | 19th 62.7% | 7th 67.0% | 1st 72.3% | 14th 64.3% | 11th 65.0% | 10th 65.3% | 14th 64.3% | 16th 64.0% | 3rd 70.7% | 8th 66.7% | 16th 64.0% | 20th 59.7% | 21st 56.3% | 3rd 70.7% | 11th 65.0% | 9th 65.7% | |
| 73.2% | 74% | 68% | 74% | 74% | 90% | 70% | 87% | 81% | 81% | 81% | 68% | 68% | 74% | 81% | 72% | 70% | 65% | 58% | 78% | 65% | 58% | |
| 50.0% | 58% | 51% | 51% | 51% | 49% | 49% | 44% | 48% | 42% | 44% | 51% | 47% | 44% | 49% | 54% | 51% | 53% | 44% | 60% | 58% | 51% | |
| 73.8% | 72% | 73% | 69% | 77% | 74% | 69% | 70% | 88% | 70% | 70% | 77% | 78% | 74% | 82% | 74% | 71% | 61% | 67% | 74% | 72% | 88% |