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 26-35. 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 | 11th 84.0% | 2nd 88.3% | 4th 87.3% | 18th 81.3% | 10th 84.5% | 14th 83.0% | 4th 87.3% | 13th 83.3% | 20th 75.3% | 9th 85.5% | 7th 86.5% | 7th 86.5% | 3rd 88.0% | 16th 81.7% | 4th 87.3% | 15th 82.0% | 17th 81.5% | 11th 84.0% | 21st 65.5% | 1st 89.0% | 19th 78.5% | |
| 79.5% | 75% | 84% | 74% | 71% | 82% | 71% | 79% | 75% | 75% | 88% | 86% | 84% | 84% | 85% | 84% | 84% | 77% | 72% | 84% | 83% | 72% | |
| 82.1% | 87% | 90% | 87% | 78% | 86% | 88% | 89% | 89% | 74% | 78% | 86% | 85% | 90% | 86% | 93% | 85% | 87% | 87% | 10% | 88% | 82% | |
| 79.2% | 76% | 82% | 91% | 79% | 83% | 81% | 88% | 76% | 66% | 79% | 78% | 83% | 82% | 72% | 73% | 73% | 74% | 84% | 81% | 91% | 72% | |
| 92.5% | 98% | 97% | 97% | 97% | 87% | 92% | 93% | 93% | 86% | 97% | 96% | 94% | 96% | 84% | 99% | 86% | 88% | 93% | 87% | 94% | 88% |