Ziya-LLaMA-13B-v1: benchmark results

Provider: Other. Access: Open.

Unified ELO 1213 ± 20, rank #2880 of 2928 rated models, from 12 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC248.65MC2 (%) (0-shot)42.2
Open LLM Leaderboard - MuSR37.51Score26.7
Open LLM Leaderboard v1 - MMLU27.04Accuracy (%) (5-shot)14.6
Open LLM Leaderboard - IFEval16.97Score7.8
Open LLM Leaderboard v1 - ARC Challenge27.73Normalized accuracy (%) (25-shot)6.9
Open LLM Leaderboard - GPQA24.92Score4.6
Open LLM Leaderboard v1 - GSM8K0Accuracy (%) (5-shot)4.6
Open LLM Leaderboard v1 - HellaSwag25.96Normalized accuracy (%) (10-shot)2.1
Open LLM Leaderboard v1 - WinoGrande49.57Accuracy (%) (5-shot)1.7
Open LLM Leaderboard - MMLU-Pro11.01Score1.5
Open LLM Leaderboard - BBH28.77Score1.4
Open LLM Leaderboard - MATH Level 50Score1.3

Interactive version: theaggregate.ai/model?slug=ziya-llama-13b-v1 · How It Works · Data refreshed daily, snapshot 2026-09-23.