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 More excited than concerned. 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 88.5% | 5th 82.5% | 6th 79.3% | 13th 75.3% | 4th 84.0% | 3rd 86.3% | 13th 75.3% | 21st 69.0% | 20th 69.3% | 17th 72.0% | 8th 77.3% | 16th 72.8% | 18th 70.8% | 15th 74.3% | 1st 89.8% | 10th 76.3% | 10th 76.3% | 12th 75.8% | 9th 76.5% | 19th 70.5% | 7th 79.0% | |
| 66.0% | 100% | 66% | 66% | 66% | 72% | 84% | 67% | 61% | 48% | 60% | 59% | 55% | 59% | 53% | 100% | 65% | 58% | 58% | 61% | 59% | 70% | |
| 76.6% | 72% | 82% | 75% | 74% | 92% | 83% | 74% | 66% | 68% | 74% | 82% | 75% | 76% | 74% | 75% | 73% | 82% | 77% | 78% | 77% | 79% | |
| 78.3% | 85% | 92% | 83% | 80% | 87% | 89% | 71% | 64% | 76% | 74% | 76% | 74% | 71% | 75% | 91% | 82% | 73% | 77% | 81% | 68% | 75% | |
| 87.7% | 97% | 90% | 93% | 81% | 85% | 89% | 89% | 85% | 85% | 80% | 92% | 87% | 77% | 95% | 93% | 85% | 92% | 91% | 86% | 78% | 92% |