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 46-55. 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 | 14th 76.8% | 8th 81.0% | 6th 81.5% | 19th 74.0% | 18th 74.3% | 12th 78.8% | 1st 84.0% | 13th 78.0% | 17th 74.8% | 15th 76.0% | 2nd 82.8% | 20th 73.8% | 3rd 82.3% | 15th 76.0% | 10th 79.5% | 4th 81.7% | 9th 80.5% | 11th 79.0% | 21st 60.8% | 4th 81.7% | 7th 81.0% | |
| 79.0% | 70% | 85% | 78% | 68% | 68% | 71% | 87% | 73% | 84% | 76% | 85% | 68% | 84% | 83% | 85% | 88% | 83% | 77% | 85% | 82% | 78% | |
| 77.0% | 74% | 82% | 82% | 69% | 65% | 82% | 84% | 81% | 70% | 70% | 85% | 72% | 83% | 74% | 79% | 79% | 75% | 84% | 75% | 75% | 76% | |
| 70.7% | 78% | 75% | 80% | 75% | 80% | 72% | 78% | 73% | 62% | 74% | 79% | 75% | 75% | 58% | 72% | 72% | 73% | 73% | 0% | 78% | 83% | |
| 85.4% | 85% | 82% | 86% | 84% | 84% | 90% | 87% | 85% | 83% | 84% | 82% | 80% | 87% | 89% | 82% | 88% | 91% | 82% | 83% | 92% | 87% |