Share your thoughts, 1 month free Claude Pro on usSee more

Competitive Programming on LiveCodeBench v6 (Pass@1 Difficulty Breakdown)

72.5Pass@1 (All)

Qwen3-235B-A22B-2507

Updated 16d ago

Evaluation Results

Method	Links
Qwen3-235B-A22B-2507 2026.04		72.5	99.71	81.73	51.88
RefineRL-4B-2507 + Skeptical@16 2026.04		67.82	100	78.85	43.36
OR-Nemotron-32B 2026.04		66.07	99.71	73.68	43.05
Qwen3-30B-A3B-2507 2026.04		64.61	99.85	75.48	38.59
OCR-Nemotron-1.1-32B 2026.04		62.25	98.84	71.15	36.8
RefineRL-4B-2507 2026.04		61.57	98.98	72.72	34.22
Qwen3-235B-A22B 2026.04		59.93	99.13	70.67	31.88
Qwen3-32B 2026.04		59.25	98.98	70.07	30.86
RefineRL-4B + Skeptical@16 2026.04		56.54	97.97	67.19	27.34
Qwen3-30B-A3B 2026.04		56	98.4	67.79	25.55
Qwen3-4B-2507 2026.04		55.21	98.84	63.7	26.25
DeepSeek-R1-0528-Qwen3-8B 2026.04		51.84	97.63	56.13	24.31
Qwen3-8B 2026.04		49.32	95.49	57.09	19.45
RefineRL-4B 2026.04		48.79	97.24	55.17	18.59
X-Coder-RL-Qwen3-8B 2026.04		48.39	85.61	56.85	22.89
Qwen3-4B 2026.04		48.29	95.35	55.05	18.59