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 | 16th 77.8% | 8th 81.3% | 7th 81.5% | 18th 75.0% | 12th 79.8% | 9th 80.8% | 1st 84.3% | 14th 78.8% | 21st 73.5% | 17th 76.5% | 4th 82.0% | 20th 75.0% | 3rd 82.5% | 18th 75.0% | 11th 80.0% | 5th 82.0% | 13th 79.0% | 10th 80.5% | 1st 84.3% | 6th 81.8% | 15th 78.3% | |
| 79.6% | 71% | 87% | 78% | 68% | 79% | 71% | 89% | 77% | 74% | 73% | 86% | 68% | 85% | 79% | 85% | 88% | 79% | 81% | 91% | 82% | 81% | |
| 78.0% | 76% | 82% | 82% | 73% | 72% | 82% | 84% | 81% | 70% | 72% | 80% | 72% | 83% | 75% | 81% | 79% | 75% | 80% | 81% | 82% | 75% | |
| 75.3% | 79% | 77% | 80% | 75% | 80% | 80% | 77% | 72% | 67% | 74% | 78% | 78% | 75% | 58% | 70% | 73% | 77% | 84% | 79% | 78% | 70% | |
| 85.1% | 85% | 79% | 86% | 84% | 88% | 90% | 87% | 85% | 83% | 87% | 84% | 82% | 87% | 88% | 84% | 88% | 85% | 77% | 86% | 85% | 87% |