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 | 13th 84.5% | 2nd 88.8% | 7th 87.3% | 18th 81.8% | 19th 81.5% | 16th 83.0% | 3rd 88.5% | 14th 83.5% | 21st 75.8% | 12th 84.7% | 1st 89.0% | 11th 84.8% | 3rd 88.5% | 20th 80.8% | 6th 87.8% | 16th 83.0% | 15th 83.3% | 9th 86.5% | 10th 85.8% | 5th 88.3% | 8th 87.0% | |
| 79.9% | 75% | 85% | 74% | 71% | 82% | 71% | 76% | 75% | 75% | 85% | 88% | 78% | 84% | 88% | 82% | 86% | 80% | 77% | 85% | 83% | 77% | |
| 87.0% | 87% | 91% | 87% | 78% | 86% | 88% | 92% | 89% | 76% | 78% | 92% | 85% | 92% | 82% | 91% | 86% | 91% | 92% | 90% | 88% | 87% | |
| 80.3% | 79% | 80% | 91% | 79% | 83% | 81% | 89% | 76% | 66% | 79% | 81% | 87% | 82% | 72% | 79% | 74% | 73% | 83% | 75% | 91% | 86% | |
| 92.6% | 97% | 99% | 97% | 99% | 75% | 92% | 97% | 94% | 86% | 97% | 95% | 89% | 96% | 81% | 99% | 86% | 89% | 94% | 93% | 91% | 98% |