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 36-45. 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 | 9th 77.0% | 1st 81.3% | 2nd 80.3% | 13th 75.8% | 5th 78.3% | 3rd 80.0% | 8th 77.5% | 10th 77.0% | 20th 72.3% | 11th 76.8% | 14th 75.3% | 17th 74.5% | 7th 78.0% | 5th 78.3% | 16th 74.5% | 18th 74.0% | 18th 74.0% | 4th 78.5% | 21st 72.0% | 12th 76.5% | 15th 75.0% | |
| 74.3% | 73% | 76% | 76% | 69% | 71% | 69% | 73% | 77% | 77% | 75% | 78% | 68% | 76% | 77% | 80% | 80% | 76% | 73% | 79% | 70% | 67% | |
| 78.2% | 73% | 85% | 79% | 78% | 83% | 80% | 88% | 82% | 71% | 79% | 71% | 74% | 85% | 84% | 79% | 77% | 79% | 74% | 67% | 79% | 76% | |
| 64.6% | 67% | 68% | 69% | 69% | 71% | 74% | 70% | 67% | 55% | 61% | 69% | 68% | 59% | 67% | 52% | 53% | 57% | 71% | 58% | 68% | ||
| 88.3% | 95% | 96% | 97% | 87% | 88% | 97% | 79% | 82% | 86% | 92% | 83% | 88% | 92% | 85% | 87% | 86% | 84% | 96% | 84% | 89% | 82% |