List your company

Code Generation on LiveCodeBench v6 (2025-02 to 2025-05)

74.1AccuracyQwen3-235B-A22B-Thinking-2507
31.66842.68453.764.716May 6, 2026May 7, 2026May 8, 2026May 9, 2026May 10, 2026May 11, 2026

Evaluation results

MethodLinks
Qwen3-235B-A22B-Thinking-2507Active=22B, Total=235B2026.0574.1———
DuSTBase Model=Qwen3-30B-Thinking2026.0572.610082.352.5
Gemini-2.5 Pro2026.0572.5———
PaCoRe hybrid compaction variant2026.0571.1———
DuSTBase Model=GPT-OSS-20B2026.0569.498.778.547.1
ZAYA1-8B + Markovian RSA (40K/4K)Active=0.7B, Total=8.0B, Configuration=40K/4K2026.0569.2———
DeepSeek-R1-0528Active=37B, Total=671B2026.0568.7———
Qwen3-30B-Thinkingtype=Base Model2026.0568.710073.747.5
Qwen3-Next-80B-A3B-ThinkActive=3B, Total=80B2026.0567.8———
OpenReasoning-Nemotron-32B2026.0567.498.473.148
Intellect-3Active=12B, Total=106B2026.0566.8———
GPT-OSS-20Btype=Base Model2026.0565.298.275.243.5
ZAYA1-8B (single rollout)Active=0.7B, Total=8.0B, Configuration=single rollout2026.0565———
TinyR1-32B2026.0564.989.574.446.3
OpenCodeReasoning-1.1-32B2026.0564.997.671.244.3
ZAYA1-8BActive=0.7B, Total=8B2026.0564.8———
Nemotron-3-Nano-30B-A3BActive=3B, Total=30B2026.0564.6———
OpenReasoning-Nemotron-14B2026.056397.672.439.3
OpenCodeReasoning-1.1-14B2026.0560.396.865.438.5
DuSTBase Model=Qwen3-4B-Thinking2026.0559.498.46834
OpenReasoning-Nemotron-7B2026.055999.26634
OLMo-3.1-32B-ThinkActive=32B, Total=32B2026.0558.3———
Mistral-Small-4-119BActive=6B, Total=119B2026.0557.9———
Klear-Reasoner-8B2026.0557.698.464.732.4
Qwen3-4B-Thinkingtype=Base Model2026.055597.660.329.9
DeepSeek-R1-0528-Qwen3-8B2026.0553.897.656.429.9
DuSTBase Model=Qwen3-30B-Instruct2026.0547.188.249.624.6
OpenCodeReasoning-1.1-7B2026.054594.455.813.1
Qwen3-30B-Instructtype=Base Model2026.0543.182.949.219
Skywork-OR1-7B2026.0540.589.54115.2
Arcee-Trinity-MiniActive=3B, Total=26B2026.0533.3———