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 56-65. 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 82.7% | 3rd 86.8% | 1st 89.5% | 20th 77.8% | 16th 80.8% | 10th 83.8% | 5th 86.0% | 17th 79.8% | 21st 75.3% | 15th 80.8% | 14th 82.5% | 11th 83.0% | 2nd 87.5% | 18th 78.3% | 8th 84.7% | 9th 84.5% | 18th 78.3% | 6th 85.8% | 12th 82.7% | 4th 86.0% | 7th 85.2% | |
| 84.4% | 82% | 96% | 86% | 71% | 80% | 82% | 85% | 76% | 77% | 80% | 88% | 77% | 94% | 85% | 91% | 95% | 82% | 85% | 87% | 89% | 84% | |
| 88.5% | 79% | 88% | 98% | 76% | 83% | 93% | 95% | 93% | 81% | 81% | 92% | 87% | 93% | 92% | 93% | 93% | 90% | 97% | 78% | 93% | 84% | |
| 67.5% | 75% | 67% | 74% | 71% | 77% | 69% | 69% | 67% | 58% | 67% | 67% | 71% | 67% | 57% | 60% | 60% | 54% | 72% | 74% | 67% | 75% | |
| 91.3% | 95% | 96% | 100% | 93% | 83% | 91% | 95% | 83% | 85% | 95% | 83% | 97% | 96% | 79% | 95% | 90% | 87% | 89% | 92% | 95% | 98% |