Code Generation on LiveCodeBench v6 (2025-02 to 2025-05)
74.1AccuracyQwen3-235B-A22B-Thinking-2507
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Qwen3-235B-A22B-Thinking-2507Active=22B, Total=235B2026.05 | 74.1 | — | — | — | |
| DuSTBase Model=Qwen3-30B-Thinking2026.05 | 72.6 | 100 | 82.3 | 52.5 | |
| Gemini-2.5 Pro2026.05 | 72.5 | — | — | — | |
| PaCoRe hybrid compaction variant2026.05 | 71.1 | — | — | — | |
| DuSTBase Model=GPT-OSS-20B2026.05 | 69.4 | 98.7 | 78.5 | 47.1 | |
| ZAYA1-8B + Markovian RSA (40K/4K)Active=0.7B, Total=8.0B, Configuration=40K/4K2026.05 | 69.2 | — | — | — | |
| DeepSeek-R1-0528Active=37B, Total=671B2026.05 | 68.7 | — | — | — | |
| Qwen3-30B-Thinkingtype=Base Model2026.05 | 68.7 | 100 | 73.7 | 47.5 | |
| Qwen3-Next-80B-A3B-ThinkActive=3B, Total=80B2026.05 | 67.8 | — | — | — | |
| OpenReasoning-Nemotron-32B2026.05 | 67.4 | 98.4 | 73.1 | 48 | |
| Intellect-3Active=12B, Total=106B2026.05 | 66.8 | — | — | — | |
| GPT-OSS-20Btype=Base Model2026.05 | 65.2 | 98.2 | 75.2 | 43.5 | |
| ZAYA1-8B (single rollout)Active=0.7B, Total=8.0B, Configuration=single rollout2026.05 | 65 | — | — | — | |
| TinyR1-32B2026.05 | 64.9 | 89.5 | 74.4 | 46.3 | |
| OpenCodeReasoning-1.1-32B2026.05 | 64.9 | 97.6 | 71.2 | 44.3 | |
| ZAYA1-8BActive=0.7B, Total=8B2026.05 | 64.8 | — | — | — | |
| Nemotron-3-Nano-30B-A3BActive=3B, Total=30B2026.05 | 64.6 | — | — | — | |
| OpenReasoning-Nemotron-14B2026.05 | 63 | 97.6 | 72.4 | 39.3 | |
| OpenCodeReasoning-1.1-14B2026.05 | 60.3 | 96.8 | 65.4 | 38.5 | |
| DuSTBase Model=Qwen3-4B-Thinking2026.05 | 59.4 | 98.4 | 68 | 34 | |
| OpenReasoning-Nemotron-7B2026.05 | 59 | 99.2 | 66 | 34 | |
| OLMo-3.1-32B-ThinkActive=32B, Total=32B2026.05 | 58.3 | — | — | — | |
| Mistral-Small-4-119BActive=6B, Total=119B2026.05 | 57.9 | — | — | — | |
| Klear-Reasoner-8B2026.05 | 57.6 | 98.4 | 64.7 | 32.4 | |
| Qwen3-4B-Thinkingtype=Base Model2026.05 | 55 | 97.6 | 60.3 | 29.9 | |
| DeepSeek-R1-0528-Qwen3-8B2026.05 | 53.8 | 97.6 | 56.4 | 29.9 | |
| DuSTBase Model=Qwen3-30B-Instruct2026.05 | 47.1 | 88.2 | 49.6 | 24.6 | |
| OpenCodeReasoning-1.1-7B2026.05 | 45 | 94.4 | 55.8 | 13.1 | |
| Qwen3-30B-Instructtype=Base Model2026.05 | 43.1 | 82.9 | 49.2 | 19 | |
| Skywork-OR1-7B2026.05 | 40.5 | 89.5 | 41 | 15.2 | |
| Arcee-Trinity-MiniActive=3B, Total=26B2026.05 | 33.3 | — | — | — |