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 | 12th 81.5% | 9th 83.5% | 5th 84.7% | 20th 75.5% | 17th 80.0% | 14th 81.3% | 11th 83.0% | 15th 81.0% | 19th 77.0% | 18th 79.0% | 1st 86.8% | 16th 80.5% | 6th 84.5% | 10th 83.5% | 13th 81.3% | 3rd 85.0% | 8th 84.0% | 2nd 85.0% | 21st 70.3% | 4th 84.8% | 7th 84.3% | |
| 77.0% | 74% | 81% | 72% | 66% | 80% | 67% | 79% | 70% | 77% | 75% | 86% | 68% | 79% | 79% | 78% | 84% | 74% | 84% | 88% | 78% | 77% | |
| 86.1% | 80% | 87% | 91% | 76% | 84% | 91% | 87% | 91% | 73% | 75% | 91% | 85% | 93% | 89% | 86% | 85% | 89% | 90% | 88% | 88% | 90% | |
| 71.3% | 79% | 73% | 79% | 73% | 68% | 75% | 74% | 70% | 62% | 72% | 84% | 75% | 70% | 71% | 68% | 74% | 78% | 75% | 10% | 82% | 85% | |
| 92.5% | 93% | 93% | 97% | 87% | 88% | 92% | 92% | 93% | 96% | 94% | 86% | 94% | 96% | 95% | 93% | 97% | 95% | 91% | 95% | 91% | 85% |