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 Indonesia. 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 | 3rd 84.8% | 9th 82.3% | 7th 83.0% | 1st 86.5% | 15th 77.5% | 18th 74.3% | 9th 82.3% | 17th 75.3% | 19th 73.8% | 11th 81.3% | 2nd 86.0% | 13th 80.7% | 6th 83.3% | 21st 73.0% | 14th 77.8% | 8th 82.7% | 16th 75.8% | 20th 73.3% | 4th 84.3% | 11th 81.3% | 4th 84.3% | |
| 77.5% | 75% | 81% | 81% | 81% | 69% | 52% | 75% | 66% | 78% | 77% | 83% | 72% | 90% | 64% | 75% | 85% | 82% | 79% | 90% | 74% | 98% | |
| 86.9% | 92% | 87% | 84% | 87% | 98% | 84% | 88% | 91% | 91% | 89% | 98% | 96% | 85% | 91% | 87% | 91% | 68% | 65% | 87% | 84% | 82% | |
| 84.0% | 91% | 90% | 90% | 96% | 85% | 86% | 94% | 74% | 71% | 85% | 83% | 85% | 83% | 67% | 79% | 85% | 79% | 79% | 85% | 91% | 87% | |
| 72.1% | 81% | 71% | 77% | 82% | 58% | 75% | 72% | 70% | 55% | 74% | 80% | 70% | 75% | 70% | 70% | 70% | 74% | 70% | 75% | 76% | 70% |