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 | 15th 81.7% | 9th 84.3% | 1st 89.0% | 19th 76.8% | 12th 82.5% | 13th 82.0% | 3rd 87.5% | 18th 78.8% | 20th 75.5% | 16th 79.5% | 10th 84.0% | 13th 82.0% | 2nd 88.5% | 17th 79.5% | 7th 86.0% | 8th 84.5% | 5th 86.5% | 6th 86.3% | 21st 60.7% | 4th 87.0% | 11th 83.8% | |
| 80.2% | 82% | 89% | 86% | 71% | 80% | 71% | 87% | 76% | 77% | 80% | 88% | 75% | 96% | 85% | 91% | 96% | 90% | 87% | 0% | 92% | 86% | |
| 89.1% | 79% | 88% | 98% | 76% | 88% | 93% | 95% | 91% | 81% | 81% | 94% | 87% | 95% | 91% | 93% | 90% | 92% | 97% | 83% | 93% | 86% | |
| 67.6% | 71% | 64% | 74% | 67% | 77% | 73% | 70% | 67% | 59% | 64% | 71% | 71% | 67% | 62% | 64% | 62% | 72% | 67% | 64% | 67% | 67% | |
| 91.9% | 95% | 96% | 98% | 93% | 85% | 91% | 98% | 81% | 85% | 93% | 83% | 95% | 96% | 80% | 96% | 90% | 92% | 94% | 96% | 96% | 96% |