Coding
LiveCodeBench
Competitive-programming problems collected after each model's training cutoff, so contamination cannot inflate the score.
LiveCodeBench is scored as a percentage of questions answered correctly. 11 of the 159 models in this index report a score for it. The highest published figure here is 83.1%, from Kimi K2 Thinking.
Reported scores
Top 11 on LiveCodeBench
Ordered by the figure each maker published. Models that have not reported this benchmark are not listed — an absent score is not a low score.
| # | Model | Published score |
|---|---|---|
| 1 | Kimi K2 ThinkingMoonshot AI | |
| 2 | GLM-4.6Z.ai (Zhipu) | |
| 3 | DeepSeek-V3.2DeepSeek | |
| 4 | Qwen3-235B-A22BAlibaba Qwen | |
| 5 | Qwen3-Coder-480B-A35BAlibaba Qwen | |
| 6 | Qwen3-32BAlibaba Qwen | |
| 7 | Qwen3-14BAlibaba Qwen | |
| 8 | QwQ-32BAlibaba Qwen | |
| 9 | Qwen3-30B-A3BAlibaba Qwen | |
| 10 | Kimi K2 InstructMoonshot AI | |
| 11 | Qwen2.5-Coder-32BAlibaba Qwen |
Where these numbers come from
Every score on this page is a published figure, taken from the model's own card, system card, technical report or release post, or from a public leaderboard. CorX Labs did not run these evaluations. Most are self-reported by the lab that built the model, which means they were produced under that lab's own choice of prompt, scaffold and number of attempts — so treat them as a starting point for a shortlist, not as a settled ranking.
A score someone other than the model's maker measured is marked Independent and names its measurer. Those are the stronger numbers on this page — an outside harness has no reason to flatter anyone — and there are not many of them.
Where a figure has not been published, the cell reads Not reported rather than an estimate. Nothing here is inferred, interpolated or guessed. Each model records the month its row was last checked. Full method and caveats.
How to read this score
LiveCodeBench collects competitive-programming problems published after each model's training cutoff, so a high score cannot come from having memorised the answer. That makes it the most contamination-resistant coding number in this index.
Where it is weak
Competitive programming is a narrow slice of software work — tight, self-contained, heavily algorithmic. It predicts very little about maintaining a large codebase.