Competitive Programming on Codeforces 2501 - 2507 benchmark leaderboard · SOTA2 Research

Competitive Programming on Codeforces 2501 - 2507

2,590ELOGPT-5.2

Evaluation Results

Method	Links
GPT-5.22026.03		2,590	99.9
Gemini-3 Pro2026.03		2,440	99.8
DeepSeek-v3.2-Speciale2026.03		2,353	99.7
Qwen-3.5-397B-A17B2026.03		2,350	99.7
Nemotron-Cascade-2-30B-A3B2026.03		2,345	99.7
Kimi-K2.5-1T-thinking2026.03		2,333	99.7
GPT-OSS-120B2026.03		2,320	99.6
Nemotron-Cascade-2-30B-A3B2026.03		2,320	99.6
GPT-o4-mini2026.03		2,266	99.5
Qwen-3.5-122B-A10B2026.03		2,233	99.4
Nemotron-3-Super-120B-A12B2026.03		2,212	99.4
Qwen-3.5-35B-A3B2026.03		2,181	99.1
o4-mini2025.12		2,169	99.1
Qwen3-235B-A22B-Thinking-25072026.03		2,119	98.6
o32025.12		2,094	98.4
Gemini-2.5-Pro-06-052025.12		2,034	98.1
Nemotron-Cascade-14B2026.03		2,004	97.9
Qwen3-235B-A22B2025.12		1,979	97.7
Nemotron-Cascade-14B-Thinking2025.12		1,932	97.2
Qwen3-Next-80B-A3B-Thinking2026.03		1,894	96.8
Qwen3-Next-80B-A3B-Thinking2025.12		1,800	95.8
Nemotron-Cascade-8B2025.12		1,789	95.7
OpenReasoning-Nemotron-32B2025.12		1,766	95.3
Nemotron-Cascade-8B-Thinking2025.12		1,740	94.7
Llama-3.3-Nemotron-Super-49B-v1.52025.12		1,716	94.1
Nemotron-3-Nano-30B-A3B2026.03		1,681	93.1
NVIDIA-Nemotron-Nano-9B-v22025.12		1,642	91.2
Klear-Reasoner-8B2025.12		1,517	86.2
Qwen3-235B-A22B2025.12		1,516	86.2
AReaL-Boba-2-14B2025.12		1,446	82.2
AceReason-Nemotron-1.0-14B2025.12		1,437	81.3
AceReason-Nemotron-1.1-7B2025.12		1,340	70.2