CodeLlama-34B-hf — benchmark results

Provider: Meta. Released 2023-08-24. Access: Open.

Unified ELO 1239 ± 17, rank #1643 of 1776 rated models, from 77 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
ToolBench - Google Sheets64.29Task Score100
ToolBench - VirtualHome24.65Task Score95.3
ToolBench - Tabletop51.32Task Score93
ToolBench - Trip Booking88.33Task Score93
ToolBench Leaderboard62.94Average Task Score93
ToolBench - Home Search88Task Score90.7
ToolBench - Open Weather96.39Task Score88.4
MMLU-by-task - Abstract Algebra34Accuracy (%)82.1
ToolBench - WebShop Short5.53Task Score72.1
MMLU-by-task - High School Physics33.11Accuracy (%)70.7
MMLU-by-task - College Chemistry39Accuracy (%)70.2
MMLU-by-task - College Mathematics34Accuracy (%)69.2

Interactive version: theaggregate.ai/model?slug=codellama-34b-hf · How the rankings work · Data refreshed daily, snapshot 2026-07-22.