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.
This blueprint operationalizes the Institute for Integrated Transitions (IFIT) report "AI on the Frontline: Evaluating Large Language Models in Real‑World Conflict Resolution" (30 July 2025). It converts the report's three scenarios (Mexico, Sudan, Syria) and ten scoring dimensions into concrete evaluation prompts. The rubrics emphasize professional conflict-advisory best practices: due diligence on context and user goals, results-over-ideology, alternatives to negotiation, trade-offs, risk disclosure, perspective-taking, local-first approaches, accompanying measures, and phased sequencing.
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude 3.5 Sonnet | Claude 3.7 Sonnet | Claude 3.5 Haiku | Claude Opus 4.1 | Claude Sonnet 4 | Deepseek Chat V3.1 | Deepseek R1 | Gemini 2.5 Flash | Gemini 2.5 Pro | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Meta Llama 3.1 405b Instruct Turbo | 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 5 | GPT OSS 120b | GPT OSS 20b | O4 Mini | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | Grok 3 | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 25th 36.6% | 19th 53.4% | 28th 29.6% | 8th 69.0% | 16th 61.0% | 12th 64.8% | 10th 65.6% | 9th 66.8% | 6th 70.6% | 3rd 73.8% | 24th 38.6% | 29th 28.6% | 30th 28.3% | 23rd 38.7% | 17th 55.2% | 22nd 41.7% | 14th 63.1% | 20th 52.2% | 21st 45.7% | 26th 36.3% | 27th 33.7% | 1st 80.9% | 2nd 79.8% | 18th 54.0% | 5th 72.2% | 4th 73.2% | 15th 62.7% | 13th 64.1% | 11th 64.9% | 7th 69.4% | |
| 62.4% | 13% | 72% | 16% | 86% | 80% | 82% | 84% | 82% | 84% | 72% | 50% | 0% | 4% | 52% | 84% | 59% | 82% | 68% | 68% | 48% | 29% | 84% | 84% | 0% | 84% | 84% | 82% | 80% | 81% | 79% | |
| 57.6% | 22% | 48% | 4% | 74% | 54% | 66% | 73% | 71% | 80% | 76% | 41% | 32% | 50% | 45% | 67% | 38% | 48% | 57% | 40% | 43% | 30% | 87% | 91% | 72% | 73% | 80% | 67% | 63% | 67% | 70% | |
| 57.2% | 41% | 51% | 45% | 65% | 64% | 69% | 57% | 65% | 69% | 72% | 39% | 32% | 33% | 30% | 58% | 39% | 71% | 51% | 39% | 34% | 38% | 83% | 79% | 68% | 78% | 79% | 65% | 69% | 62% | 72% | |
| 66.3% | 67% | 73% | 50% | 85% | 90% | 71% | 77% | 75% | 73% | 75% | 61% | 56% | 0% | 61% | 63% | 56% | 69% | 69% | 67% | 56% | 55% | 85% | 88% | 0% | 81% | 79% | 79% | 75% | 75% | 77% | |
| 50.3% | 24% | 34% | 15% | 63% | 46% | 65% | 66% | 54% | 64% | 74% | 32% | 23% | 37% | 18% | 55% | 28% | 64% | 41% | 38% | 28% | 22% | 69% | 78% | 67% | 60% | 78% | 55% | 60% | 77% | 74% | |
| 46.2% | 26% | 37% | 21% | 50% | 48% | 44% | 42% | 65% | 56% | 80% | 24% | 29% | 21% | 32% | 43% | 23% | 66% | 41% | 42% | 19% | 26% | 76% | 81% | 59% | 56% | 60% | 43% | 51% | 57% | 68% | |
| 59.6% | 48% | 63% | 33% | 73% | 63% | 75% | 73% | 73% | 78% | 73% | 35% | 28% | 33% | 38% | 53% | 48% | 73% | 58% | 48% | 48% | 53% | 88% | 73% | 75% | 78% | 70% | 65% | 63% | 55% | 55% | |
| 53.4% | 43% | 53% | 53% | 60% | 47% | 56% | 61% | 56% | 75% | 74% | 34% | 28% | 38% | 31% | 52% | 39% | 53% | 42% | 33% | 27% | 29% | 77% | 79% | 74% | 70% | 61% | 59% | 70% | 63% | 65% | |
| 49.2% | 45% | 50% | 29% | 65% | 57% | 55% | 57% | 60% | 56% | 68% | 31% | 29% | 39% | 41% | 22% | 45% | 42% | 43% | 36% | 24% | 21% | 79% | 65% | 71% | 70% | 68% | 49% | 46% | 47% | 65% |