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 | 8th 85.8% | 2nd 88.0% | 1st 88.8% | 10th 84.5% | 18th 80.3% | 12th 82.5% | 7th 85.8% | 12th 82.5% | 20th 76.5% | 19th 80.2% | 3rd 87.5% | 4th 87.3% | 9th 85.3% | 16th 80.8% | 6th 86.0% | 15th 81.3% | 17th 80.5% | 12th 82.5% | 21st 65.5% | 4th 87.3% | 11th 82.7% | |
| 82.0% | 81% | 85% | 86% | 77% | 79% | 73% | 81% | 76% | 83% | 85% | 89% | 84% | 80% | 90% | 85% | 87% | 81% | 78% | 80% | 84% | 77% | |
| 85.0% | 90% | 89% | 87% | 90% | 76% | 83% | 90% | 92% | 75% | 78% | 86% | 87% | 86% | 81% | 91% | 81% | 81% | 87% | 85% | 85% | 86% | |
| 75.8% | 80% | 80% | 90% | 78% | 83% | 82% | 81% | 74% | 65% | 72% | 86% | 87% | 83% | 73% | 75% | 74% | 74% | 82% | 0% | 91% | 82% | |
| 88.9% | 92% | 98% | 92% | 93% | 83% | 92% | 91% | 88% | 83% | 86% | 89% | 91% | 92% | 79% | 93% | 83% | 86% | 83% | 97% | 89% | 86% |