Skip to main content
Evaluation sources/LiveBench Coding
ObservingCoding

LiveBench Coding

LiveBench · Public model evaluation results from LiveBench Coding.

Official evaluation
Source description

This source measures concrete delivery performance in Coding; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

Claude Opus 5.578.731478.72026-06-25
DeepSeek V4.1 Flash78.378478.42026-06-25
Claude Fable 5.174.186474.22026-06-25
Claude Fable 571.699871.72026-06-25
Claude Opus 571.699471.72026-06-25
Muse Spark 1.370.879670.92026-06-25
Claude Sonnet 5.570.334470.32026-06-25
Muse Wonder69.908469.92026-06-25
Kimi K369.881269.92026-06-25
GLM 5.368.125468.12026-06-25
Qwen3.8 Max67.936867.92026-06-25
Claude Sonnet 567.908467.92026-06-25
GPT-5.6 Sol67.303667.32026-06-25
GPT-6 Astra66.537266.52026-06-25
GPT-6.1 Sol66.35766.42026-06-25
Muse Spark 1.165.984666.02026-06-25
GLM-5.3 Flash65.640665.62026-06-25
Muse Spark 1.265.56265.62026-06-25
Claude Haiku 5.565.448265.42026-06-25
GPT-5.565.253665.32026-06-25
Mistral Large 465.166465.22026-06-25
Grok 4.664.922464.92026-06-25
GPT-6 Sol64.43464.42026-06-25
GPT-5.6 Terra64.26864.32026-06-25

Page 1 of 3

Frequently asked questions