LiveCodeBench

Source-qualified evaluations, report statistics and safety observations.

Kimi-k1.6-IOI

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.8014772727272726percent

Kimi-k1.6-IOI-high

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.8602272727272726percent

Llama-3_1-Nemotron-Nano-8B-v1

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.6443181818181819percent

Llama-3_1-Nemotron-Ultra-253B-v1

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.7772727272727273percent

MetaStone-L1-7B

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.5409090909090909percent

Mistral-Large

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.3729545454545455percent

O1-2024-12-17 (High)

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.8318181818181819percent

O1-2024-12-17 (Low)

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.759090909090909percent

O1-2024-12-17 (Med)

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.7829545454545455percent

O1-Mini-2024-09-12

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.6840909090909091percent

O1-Preview-2024-09-12

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.5556818181818182percent

O3-Mini-2025-01-31 (High)

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.8045454545454546percent

O3-Mini-2025-01-31 (Low)

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.7454545454545455percent

O3-Mini-2025-01-31 (Med)

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.7920454545454545percent

O4-Mini (High)

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.8556818181818181percent

QwQ-Max-Preview

MetricValueUnit
LiveCodeBench v5 · derived cohort mean0.8percent

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