LiveCodeBench

Source-qualified evaluations, report statistics and safety observations.

AzeroGPT-64b

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.2203409090909091percent

Claude-3.5-Sonnet-20240620

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.48034090909090904percent

Claude-3.5-Sonnet-20241022

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.5146590909090909percent

Claude-3-Haiku

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.22181818181818183percent

Codestral-Latest

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.3532954545454545percent

DeepSeek-R1-Lite-Preview

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.6307954545454545percent

DeepSeek-R1-Preview

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.7788636363636364percent

Gemini-2.5-Pro

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.8465909090909091percent

Gemini-Flash-1.5-002

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.36125percent

Gemini-Flash-2.0-Exp

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.41590909090909095percent

Gemini-Pro-1.5-002

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.42090909090909095percent

GPT-4O-2024-05-13

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.4343181818181818percent

GPT-4O-2024-08-06

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.4018181818181818percent

GPT-4O-mini-2024-07-18

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.3718181818181818percent

GPT-4-Turbo-2024-04-09

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.39090909090909093percent

Grok-3-Mini (High)

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.8136363636363636percent

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace