List your company

Context-aware turn-taking on SPGI

96.86I1 ScoreLLaMA3.1-8b-instruct
67.500875.122982.74590.3671Mar 12, 2026

Evaluation results

MethodLinks
LLaMA3.1-8b-instructEvaluation Protocol=Zero-shot, System Prompt Frequency=Single2026.0396.8665.3220.754.5844.3637.244.76
LLaMA3.1-8b-instructEvaluation Protocol=Zero-shot, System Prompt Frequency=Repeated twice2026.0396.8665.3220.754.5844.3637.244.76
Qwen3-4b-instructEvaluation Protocol=Zero-shot, System Prompt Frequency=Single2026.0394.9455.0716.9910.3442.2536.8142.6
Qwen3-4b-instructEvaluation Protocol=Zero-shot, System Prompt Frequency=Repeated twice2026.0394.9455.0716.9910.3442.2536.8142.6
Qwen3-8bEvaluation Protocol=Zero-shot, System Prompt Frequency=Single2026.0394.9443.733.711.2842.4639.3142.73
Qwen3-8bEvaluation Protocol=Zero-shot, System Prompt Frequency=Repeated twice2026.0394.9443.733.711.2842.4639.3142.73
Qwen2.5-7bEvaluation Protocol=Zero-shot, System Prompt Frequency=Single2026.0389.2867.9525.7216.348.1543.6848.48
Qwen2.5-7bEvaluation Protocol=Zero-shot, System Prompt Frequency=Repeated twice2026.0389.2867.9525.7216.348.1543.6848.48
gpt-5.2Evaluation Protocol=Zero-shot, System Prompt Frequency=Single2026.0385.331.5475.4849.4556.9656.9356.94
gpt-5.2Evaluation Protocol=Zero-shot, System Prompt Frequency=Repeated twice2026.0385.331.5475.4849.4556.9656.9356.94
Mistral-7b-instructEvaluation Protocol=Zero-shot, System Prompt Frequency=Single2026.0384.672.0324.0319.5249.0144.849.33
Mistral-7b-instructEvaluation Protocol=Zero-shot, System Prompt Frequency=Repeated twice2026.0384.672.0324.0319.5249.0144.849.33
gemini-3.1-proEvaluation Protocol=Zero-shot, System Prompt Frequency=Single2026.0379.3530.3191.3269.0764.5763.9364.45
gemini-3.1-proEvaluation Protocol=Zero-shot, System Prompt Frequency=Repeated twice2026.0379.3530.3191.3269.0764.5763.9364.45
gpt-oss-20bEvaluation Protocol=Zero-shot, System Prompt Frequency=Single2026.0368.6322.8470.1848.3549.6249.3549.54
gpt-oss-20bEvaluation Protocol=Zero-shot, System Prompt Frequency=Repeated twice2026.0368.6322.8470.1848.3549.6249.3549.54