Code Generation on LiveCodeBench v6 (Score (%))

91.7Score

Gemini-3-Pro-preview

Updated 1mo ago

Evaluation Results

Method	Links
Gemini-3-Pro-preview 2026.03		91.7
Gemini-3-Flash-preview 2026.03		90.8
Claude-Opus-4.5 2026.03		87.1
GPT-5.1 2026.03		87
GLM-4.7 2026.03		84.9
DeepSeek-v3.2 2026.03		83.3
Kimi-K2-Thinking 2026.03		83.1
IQuest-Coder-V1-40B-Loop-Thinking 2026.03		81.1
IQuest-Coder-V1-40B-Thinking 2026.03		77.7
Qwen3-235B-A22B-Thinking-2507 2026.03		74.1
Claude-Sonnet-4.5 2026.03		73
IQuest-Coder-V1-14B-Thinking 2026.03		66.3
Qwen3-Coder-480B-A35B-Instruct 2026.03		53.9
Kimi-K2-Instruct-0905 2026.03		53.7
Qwen3-235B-A22B-Instruct-2507 2026.03		51.8
IQuest-Coder-V1-40B-Loop-Instruct 2026.03		48.5
IQuest-Coder-V1-40B-Instruct 2026.03		46.9
IQuest-Coder-V1-14B-Instruct 2026.03		40
Kimi-Dev-72B 2026.03		40
IQuest-Coder-V1-7B-Thinking 2026.03		36.6
Qwen3-Coder-30B-A3B-Instruct 2026.03		36
DataFlow-Code-1K 2025.12		33.7
Qwen2.5-14B-Instruct 2025.12		33.4
DataFlow-Code-5K 2025.12		33.2
DataFlow-Code-10K 2025.12		33.2
KAT-Dev 2026.03		32.6
Code Alpaca-1K 2025.12		28.2
Qwen2.5-Coder-32B-Instruct 2026.03		27.4
DataFlow-Code-5K 2025.12		26.4
DataFlow-Code-10K 2025.12		26
DataFlow-Code-1K 2025.12		25.7
IQuest-Coder-V1-7B-Instruct 2026.03		24.6
Qwen2.5-Coder-14B-Instruct 2026.03		24.6
Qwen2.5-7B-Instruct 2025.12		23.4
Self-OSS 2025.12		22.3
Seed-Coder-8B-Instruct 2026.03		22.3
Self-OSS 2025.12		21.4
DeepSeek-Coder-V2-Lite-Instruct 2026.03		19.4
Qwen2.5-Coder-7B-Instruct 2026.03		18.9
Code Alpaca-1K 2025.12		18.7
KAT-Dev-72B-Exp 2026.03		16