LiveCodeBench v6
LiveCodeBench v6 is a named release slice used in provider comparison tables. Keeping it separate prevents v6 results from being mixed into older or rolling LiveCodeBench windows.
46 models
Higher is better.
- 1Qwen3.8-Omni-FlashAlibaba92.6
- 2Solar Open 2Upstage92.4
- 3Qwen3.8-Flash-NextAlibaba91.9
- 4Qwen3.7 MaxAlibaba91.6
- 5dots3-note PreviewDots Studio91.5
- 6Qwen3.8-27BAlibaba90.3
- 7Ternary Bonsai 2 27BPrism ML90.1
- 8Kimi K2.6Moonshot AI89.6
- 9Qwen3.7 PlusAlibaba89.6
- 10Nemotron 3 UltraNVIDIA89.0
- 11Nemotron 3.5 Super VL 120B A12BNVIDIA88.2
- 12MAI-Thinking-1Microsoft87.7
- 13Qwen3.6 PlusAlibaba87.1
- 14Step 3.5 FlashStepFun86.4
- 15Kimi K2.5 (Reasoning)Moonshot AI85.0
- 16Kimi K2.5Moonshot AI85.0
- 17GLM-4.7Z.AI84.9
- 18Claude Opus 4.5Anthropic84.8
- 19A.X K2SK Telecom84.0
- 20Qwen3.6-27BAlibaba83.9
- 21Qwen3.5 397BAlibaba83.6
- 22Mellum2.1-12B-A2.5B-ThinkingJetBrains82.0
- 23Qwen3.5-27BAlibaba80.7
- 24MiMo-V2-FlashXiaomi80.6
- 25Qwen3.6-35B-A3BAlibaba80.4
- 26Gemma 4 31BGoogle80.0
- 27Qwen3.5-122B-A10BAlibaba78.9
- 28Gemma 4 26B A4BGoogle77.1
- 29Qwen3.5-35B-A3BAlibaba74.6
- 30Granite 4.2 8BIBM73.2
- 31Gemma 4 12BGoogle72.0
- 32MiniCPM5-2BOpenBMB69.1
- 33Nemotron 3 Nano 30BNVIDIA68.3
- 34BTL-4Bad Theory Labs66.1
- 35ZAYA1-8BZyphra65.8
- 36ZAYA1-74B-PreviewZyphra65.7
- 37GLM-4.7-FlashZ.AI64.0
- 38LFM2.5-2.6BLiquid AI59.4
- 39Kimi K2Moonshot AI53.7
- 40Gemma 4 E4BGoogle52.0
About this benchmark
- Metric
- Provider-published v6 competitive programming results
- Tasks
- Fresh programming problems
- Authors
- LiveCodeBench maintainers (2026)
Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.
All results
| 1 | Qwen3.8-Omni-Flash Alibaba | 92.6 |
| 2 | Solar Open 2 Upstage | 92.4 |
| 3 | Qwen3.8-Flash-Next Alibaba | 91.9 |
| 4 | Qwen3.7 Max Alibaba | 91.6 |
| 5 | dots3-note Preview Dots Studio | 91.5 |
| 6 | Qwen3.8-27B Alibaba | 90.3 |
| 7 | Ternary Bonsai 2 27B Prism ML | 90.1 |
| 8 | Kimi K2.6 Moonshot AI | 89.6 |
| 9 | Qwen3.7 Plus Alibaba | 89.6 |
| 10 | Nemotron 3 Ultra NVIDIA | 89.0 |
| 11 | Nemotron 3.5 Super VL 120B A12B NVIDIA | 88.2 |
| 12 | MAI-Thinking-1 Microsoft | 87.7 |
| 13 | Qwen3.6 Plus Alibaba | 87.1 |
| 14 | Step 3.5 Flash StepFun | 86.4 |
| 15 | Kimi K2.5 (Reasoning) Moonshot AI | 85.0 |
| 16 | Kimi K2.5 Moonshot AI | 85.0 |
| 17 | GLM-4.7 Z.AI | 84.9 |
| 18 | Claude Opus 4.5 Anthropic | 84.8 |
| 19 | A.X K2 SK Telecom | 84.0 |
| 20 | Qwen3.6-27B Alibaba | 83.9 |
| 21 | Qwen3.5 397B Alibaba | 83.6 |
| 22 | Mellum2.1-12B-A2.5B-Thinking JetBrains | 82.0 |
| 23 | Qwen3.5-27B Alibaba | 80.7 |
| 24 | MiMo-V2-Flash Xiaomi | 80.6 |
| 25 | Qwen3.6-35B-A3B Alibaba | 80.4 |
| 26 | Gemma 4 31B Google | 80.0 |
| 27 | Qwen3.5-122B-A10B Alibaba | 78.9 |
| 28 | Gemma 4 26B A4B Google | 77.1 |
| 29 | Qwen3.5-35B-A3B Alibaba | 74.6 |
| 30 | Granite 4.2 8B IBM | 73.2 |
| 31 | Gemma 4 12B Google | 72.0 |
| 32 | MiniCPM5-2B OpenBMB | 69.1 |
| 33 | Nemotron 3 Nano 30B NVIDIA | 68.3 |
| 34 | BTL-4 Bad Theory Labs | 66.1 |
| 35 | ZAYA1-8B Zyphra | 65.8 |
| 36 | ZAYA1-74B-Preview Zyphra | 65.7 |
| 37 | GLM-4.7-Flash Z.AI | 64.0 |
| 38 | LFM2.5-2.6B Liquid AI | 59.4 |
| 39 | Kimi K2 Moonshot AI | 53.7 |
| 40 | Gemma 4 E4B Google | 52.0 |
| 41 | Qwen3 235B 2507 Alibaba | 51.8 |
| 42 | Magistral Medium Mistral | 50.3 |
| 43 | Gemma 4 E2B Google | 44.0 |
| 44 | Mellum2-12B-A2.5B-Instruct JetBrains | 37.2 |
| 45 | MiniCPM5-1B OpenBMB | 33.5 |
| 46 | Mistral Medium 3 Mistral | 30.3 |