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 Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT 5 | GPT 5.1 | GPT OSS 120b | GPT OSS 20b | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 7th 86.3% | 3rd 87.3% | 20th 79.5% | 16th 82.3% | 16th 82.3% | 13th 83.0% | 12th 83.3% | 21st 74.8% | 10th 84.7% | 9th 85.0% | 5th 87.0% | 11th 84.0% | 1st 88.3% | 14th 82.8% | 8th 85.8% | 1st 88.3% | 15th 82.5% | 19th 80.3% | 6th 86.5% | 18th 80.8% | 3rd 87.3% | |
| 77.7% | 79% | 74% | 71% | 72% | 82% | 71% | 75% | 75% | 85% | 79% | 82% | 88% | 83% | 86% | 79% | 82% | 77% | 66% | 76% | 72% | 77% | |
| 85.1% | 81% | 87% | 78% | 90% | 78% | 88% | 89% | 74% | 78% | 84% | 90% | 89% | 92% | 85% | 84% | 91% | 82% | 87% | 88% | 79% | 94% | |
| 81.1% | 87% | 91% | 79% | 81% | 83% | 81% | 76% | 64% | 79% | 83% | 81% | 76% | 79% | 74% | 83% | 87% | 75% | 82% | 91% | 84% | 87% | |
| 91.6% | 98% | 97% | 90% | 86% | 86% | 92% | 93% | 86% | 97% | 94% | 95% | 83% | 99% | 86% | 97% | 93% | 96% | 86% | 91% | 88% | 91% |