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 Kazakhstan. 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 | 9th 74.3% | 15th 72.3% | 12th 74.0% | 1st 80.7% | 4th 76.3% | 19th 70.7% | 9th 74.3% | 13th 73.0% | 8th 75.0% | 13th 73.0% | 17th 71.3% | 7th 75.3% | 21st 69.7% | 20th 70.0% | 3rd 78.3% | 5th 76.0% | 16th 71.7% | 18th 71.3% | 2nd 78.7% | 9th 74.3% | 6th 75.3% | |
| 71.8% | 69% | 66% | 64% | 76% | 76% | 72% | 71% | 76% | 76% | 72% | 64% | 76% | 71% | 74% | 76% | 69% | 68% | 69% | 76% | 76% | 71% | |
| 59.5% | 62% | 62% | 66% | 71% | 66% | 57% | 61% | 48% | 56% | 57% | 61% | 62% | 49% | 47% | 70% | 66% | 58% | 51% | 66% | 51% | 62% | |
| 91.0% | 92% | 89% | 92% | 95% | 87% | 83% | 91% | 95% | 93% | 90% | 89% | 88% | 89% | 89% | 89% | 93% | 89% | 94% | 94% | 96% | 93% |