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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 89.0% | 8th 80.5% | 13th 77.3% | 9th 80.0% | 18th 73.5% | 20th 70.5% | 11th 79.0% | 17th 74.5% | 19th 72.5% | 16th 76.0% | 1st 93.0% | 14th 77.3% | 7th 80.8% | 4th 86.0% | 5th 84.0% | 10th 79.8% | 15th 76.3% | 12th 77.5% | 3rd 86.5% | 6th 83.0% | 21st 65.5% | |
| 64.3% | 64% | 71% | 59% | 52% | 59% | 45% | 66% | 52% | 58% | 54% | 100% | 57% | 73% | 80% | 72% | 77% | 64% | 62% | 71% | 64% | 51% | |
| 83.6% | 100% | 94% | 76% | 78% | 77% | 77% | 84% | 78% | 80% | 78% | 100% | 78% | 78% | 100% | 97% | 77% | 74% | 75% | 80% | 94% | 80% | |
| 88.0% | 97% | 75% | 93% | 95% | 79% | 80% | 87% | 91% | 81% | 95% | 79% | 95% | 83% | 84% | 88% | 83% | 88% | 96% | 97% | 95% | ||
| 82.5% | 95% | 82% | 81% | 95% | 79% | 80% | 79% | 77% | 71% | 77% | 93% | 79% | 89% | 80% | 79% | 82% | 79% | 77% | 98% | 79% |