Inference
Explore
Leaderboard
Benchmarks
Labs
Run locally
Search
⌘K
EN
English
Русский
Локально
中文
本地运行
12 Nov
2026
Benchmarks
/
LiveCodeBench v5
LiveCodeBench maintainers
LiveCodeBench v5
Not in index
Coding
Best in coding
Source ↗
Models
?
Models with a result.
9
Top result
?
Best result on this benchmark.
—
Top-3 spread
?
Points from first to third.
—
Year
?
Year of release.
2025
Results
9 results
Export
CSV
Export
JSON
#
Model
Result
?
The score from the source.
—
IN
Ling 3.0 Flash
82.8
%
—
Qwen3 235B-A22B (Reasoning)
70.7
%
—
Qwen3 32B (Reasoning)
65.7
%
—
Nemotron 3 Nano Omni 30B A3B
63.2
%
—
QwQ-32B
62.7
%
—
Magistral Medium
59.4
%
—
Magistral Small
55.8
%
—
Qwen3 235B-A22B
35.3
%
—
Qwen3 32B
31.3
%