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 | 14th 81.3% | 4th 86.0% | 1st 89.0% | 20th 77.0% | 13th 81.5% | 15th 81.0% | 6th 85.5% | 17th 79.8% | 21st 75.5% | 18th 79.5% | 5th 85.8% | 10th 83.0% | 2nd 88.0% | 16th 79.8% | 7th 84.5% | 8th 84.0% | 11th 82.8% | 9th 83.8% | 12th 82.5% | 3rd 86.3% | 19th 78.5% | |
| 83.1% | 78% | 96% | 86% | 71% | 81% | 71% | 83% | 76% | 75% | 78% | 95% | 77% | 94% | 85% | 89% | 96% | 82% | 72% | 87% | 89% | 85% | |
| 88.1% | 76% | 88% | 98% | 76% | 76% | 93% | 95% | 93% | 81% | 80% | 94% | 89% | 95% | 92% | 93% | 90% | 90% | 97% | 78% | 93% | 84% | |
| 67.7% | 75% | 64% | 74% | 71% | 73% | 69% | 70% | 67% | 61% | 67% | 71% | 71% | 67% | 62% | 60% | 60% | 67% | 72% | 71% | 67% | 62% | |
| 91.5% | 96% | 96% | 98% | 90% | 96% | 91% | 94% | 83% | 85% | 93% | 83% | 95% | 96% | 80% | 96% | 90% | 92% | 94% | 94% | 96% | 83% |