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 Morocco. 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 | 3rd 66.0% | 4th 62.7% | 7th 61.3% | 7th 61.3% | 1st 71.3% | 16th 53.7% | 21st 47.0% | 18th 51.7% | 12th 58.7% | 11th 60.0% | 5th 62.3% | 17th 53.0% | 14th 56.3% | 9th 61.3% | 2nd 66.3% | 6th 61.7% | 13th 57.7% | 9th 61.3% | 19th 51.0% | 19th 51.0% | 15th 55.7% | |
| 66.8% | 79% | 74% | 74% | 74% | 74% | 70% | 49% | 62% | 67% | 66% | 74% | 62% | 59% | 69% | 74% | 74% | 62% | 72% | 62% | 51% | 54% | |
| 55.0% | 58% | 58% | 63% | 63% | 82% | 45% | 45% | 46% | 56% | 58% | 52% | 46% | 52% | 52% | 72% | 60% | 50% | 51% | 44% | 46% | 57% | |
| 54.1% | 61% | 56% | 47% | 47% | 58% | 46% | 47% | 47% | 53% | 56% | 61% | 51% | 58% | 63% | 53% | 51% | 61% | 61% | 47% | 56% | 56% |