WizardCoder-Python-34B-V1.0 — benchmark results

Provider: Other. Access: Open.

Unified ELO 1314 ± 18, rank #1459 of 1716 rated models, from 69 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - College Physics42.16Accuracy (%)98.8
MMLU-by-task - High School Mathematics34.44Accuracy (%)96.9
MMLU-by-task - Elementary Mathematics41.01Accuracy (%)92.4
MMLU-by-task - College Computer Science52Accuracy (%)91.1
MMLU-by-task - High School Computer Science62Accuracy (%)87.1
MMLU-by-task - High School Physics35.76Accuracy (%)84.4
MMLU-by-task - Formal Logic38.89Accuracy (%)83.9
MMLU-by-task - Computer Security70Accuracy (%)82.6
InfiBench52.59Score (%)81.9
BigCode Models Leaderboard70.7HumanEval Python Pass@1 (%)81.4
MMLU-by-task - College Mathematics36Accuracy (%)80.3
MMLU-by-task - Moral Scenarios38.1Accuracy (%)78.4

Interactive version: aibenchmarks.dev/model?slug=wizardcoder-python-34b-v1-0 · How the rankings work · Data refreshed daily, snapshot 2026-07-09.