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 Turkey. Source: Global Dialogues GD1 (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 89.0% | 13th 77.3% | 8th 80.0% | 11th 77.7% | 19th 73.5% | 21st 70.5% | 18th 74.5% | 20th 72.5% | 17th 76.0% | 14th 77.3% | 7th 80.8% | 3rd 86.0% | 4th 84.0% | 9th 79.8% | 5th 83.5% | 10th 79.5% | 16th 76.3% | 12th 77.5% | 6th 83.0% | 15th 76.5% | 1st 90.3% | |
| 63.7% | 64% | 59% | 52% | 58% | 59% | 45% | 52% | 58% | 54% | 57% | 73% | 80% | 72% | 77% | 70% | 66% | 64% | 62% | 64% | 51% | 100% | |
| 83.0% | 100% | 76% | 78% | 78% | 77% | 77% | 78% | 80% | 78% | 78% | 78% | 100% | 97% | 77% | 87% | 80% | 74% | 75% | 94% | 80% | 100% | |
| 88.8% | 97% | 93% | 95% | 95% | 79% | 80% | 91% | 81% | 95% | 95% | 83% | 84% | 88% | 83% | 82% | 90% | 88% | 96% | 95% | 96% | 79% | |
| 81.8% | 95% | 81% | 95% | 80% | 79% | 80% | 77% | 71% | 77% | 79% | 89% | 80% | 79% | 82% | 95% | 82% | 79% | 77% | 79% | 79% | 82% |