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 GD2 (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 | 1st 95.0% | 6th 81.7% | 7th 79.3% | 10th 77.3% | 4th 84.3% | 5th 84.3% | 13th 74.7% | 19th 68.3% | 17th 72.0% | 16th 73.3% | 11th 75.0% | 21st 67.0% | 19th 68.3% | 15th 73.3% | 2nd 91.7% | 8th 78.7% | 14th 74.0% | 11th 75.0% | 9th 78.3% | 18th 71.7% | 3rd 89.3% | |
| 91.0% | 96% | 88% | 96% | 88% | 98% | 81% | 87% | 91% | 93% | 91% | 96% | 89% | 84% | 96% | 93% | 87% | 91% | 93% | 94% | 85% | 93% | |
| 75.6% | 89% | 91% | 81% | 78% | 75% | 88% | 70% | 61% | 75% | 72% | 74% | 71% | 62% | 72% | 82% | 75% | 71% | 75% | 80% | 71% | 75% | |
| 66.7% | 100% | 66% | 61% | 66% | 80% | 84% | 67% | 53% | 48% | 57% | 55% | 41% | 59% | 52% | 100% | 74% | 60% | 57% | 61% | 59% | 100% |