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 36-45. 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 | 14th 81.5% | 5th 83.8% | 9th 83.5% | 21st 76.8% | 20th 77.3% | 15th 81.3% | 2nd 86.0% | 16th 81.0% | 19th 78.0% | 18th 79.3% | 1st 87.3% | 13th 81.5% | 3rd 85.3% | 17th 80.3% | 5th 83.8% | 4th 84.0% | 11th 83.0% | 5th 83.8% | 12th 82.8% | 8th 83.5% | 9th 83.5% | |
| 76.8% | 72% | 81% | 72% | 65% | 73% | 67% | 78% | 70% | 80% | 75% | 86% | 71% | 77% | 79% | 79% | 84% | 79% | 82% | 83% | 75% | 84% | |
| 85.0% | 80% | 87% | 87% | 76% | 72% | 91% | 89% | 89% | 72% | 75% | 92% | 85% | 95% | 82% | 91% | 87% | 91% | 86% | 88% | 85% | 84% | |
| 73.6% | 79% | 74% | 79% | 79% | 76% | 75% | 81% | 70% | 64% | 72% | 77% | 76% | 73% | 66% | 71% | 67% | 70% | 73% | 62% | 83% | 79% | |
| 93.6% | 95% | 93% | 96% | 87% | 88% | 92% | 96% | 95% | 96% | 95% | 94% | 94% | 96% | 94% | 94% | 98% | 92% | 94% | 98% | 91% | 87% |