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 18-25. 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 | 4th 87.8% | 3rd 87.8% | 2nd 88.5% | 10th 85.0% | 13th 82.8% | 17th 81.8% | 5th 87.3% | 13th 82.8% | 20th 77.5% | 19th 80.3% | 1st 89.5% | 6th 87.0% | 12th 83.0% | 21st 74.3% | 7th 86.8% | 13th 82.8% | 16th 82.5% | 17th 81.8% | 9th 85.5% | 7th 86.8% | 11th 84.5% | |
| 81.3% | 80% | 85% | 87% | 79% | 76% | 73% | 81% | 74% | 83% | 88% | 89% | 86% | 82% | 83% | 85% | 87% | 78% | 67% | 79% | 83% | 82% | |
| 85.9% | 91% | 87% | 86% | 90% | 85% | 80% | 86% | 91% | 75% | 78% | 94% | 88% | 81% | 84% | 86% | 89% | 87% | 89% | 85% | 86% | ||
| 80.0% | 83% | 81% | 90% | 78% | 87% | 82% | 89% | 76% | 73% | 72% | 81% | 83% | 74% | 53% | 82% | 75% | 84% | 82% | 81% | 91% | 82% | |
| 89.3% | 97% | 98% | 91% | 93% | 83% | 92% | 93% | 90% | 79% | 83% | 94% | 91% | 93% | 80% | 96% | 83% | 79% | 91% | 93% | 88% | 88% |