Coding
LiveBench Coding Leaderboard
LiveBench Coding evaluates code generation and completion on fresh, contamination-free programming tasks that are updated regularly.
Source: livebench19 open models ranked+51 proprietaryData through Jun 2026
Open models ranked on LiveBench Coding
# shows rank among open models / rank overall (including proprietary).
| # | Model | Score | VRAM @ Q4 |
|---|---|---|---|
| 1 / 16 | Kimi K3 · 2779.9B | 81.5 | ~1674 GB |
| 2 / 23 | DeepSeek V4.1 Flash · 763.2B | 80.0 | ~458 GB |
| 3 / 25 | GLM 5.2 · 753.3B | 79.7 | ~456 GB |
| 4 / 27 | GLM 5.3 · 753.3B | 79.0 | ~456 GB |
| 5 / 28 | GLM 5.3 Flash · 321.3B | 79.0 | ~195 GB |
| 6 / 31 | Kimi K2.6 · 1026.9B | 78.6 | ~620 GB |
| 7 / 40 | DeepSeek V4 Pro 0813 · 1650.5B | 77.2 | ~991 GB |
| 8 / 44 | Smaug Flash · 304.2B | 77.1 | ~609 GB |
| 9 / 51 | Qwen3.8 27B · 27.8B | 75.7 | ~17 GB |
| 10 / 53 | DeepSeek V4 Flash 0731 · 304.2B | 75.0 | ~183 GB |
| 11 / 55 | Kimi K2.7 Code · 1026.9B | 74.0 | ~620 GB |
| 12 / 57 | Qwen3.8 Flash Next · 180.0B | 72.5 | ~108 GB |
| 13 / 59 | Qwen3.6 27B · 27.8B | 71.8 | ~17 GB |
| 14 / 61 | Inkling · 952.4B | 71.0 | ~572 GB |
| 15 / 63 | NVIDIA Nemotron 3 Ultra 550B A55B BF16 · 560.5B | 70.7 | ~370 GB |
| 16 / 64 | DeepSeek V4 Pro · 1598.8B | 70.0 | ~960 GB |
| 17 / 66 | DeepSeek V4 Flash · 290.9B | 69.2 | ~175 GB |
| 18 / 68 | DeepSeek V4 Flash Vision Exp · 304.6B | 68.2 | ~183 GB |
| 19 / 69 | MiniMax M3 · 427.0B | 68.2 | ~257 GB |
Score vs model size
Which models give the most quality for their size — the ones worth running locally.
- Qwen3.8 27B, 28B, score 75.7 — on the efficiency frontier (best score at its size or smaller).
- Smaug Flash, 304B, score 77.1 — on the efficiency frontier (best score at its size or smaller).
- GLM 5.3 Flash, 321B, score 79.0 — on the efficiency frontier (best score at its size or smaller).
- GLM 5.2, 753B, score 79.7 — on the efficiency frontier (best score at its size or smaller).
- DeepSeek V4.1 Flash, 763B, score 80.0 — on the efficiency frontier (best score at its size or smaller).
- Kimi K3, 2.8T, score 81.5 — on the efficiency frontier (best score at its size or smaller).
LiveBench Coding: frequently asked questions
- What is the best open LLM on LiveBench Coding?
- Kimi K3 is the top open model on LiveBench Coding, scoring 81.5. Among all models tested — including proprietary ones — it ranks #15. The top model overall is Claude Sonnet 5.5 Max (Anthropic) at 91.4.
- What's the best LiveBench Coding model you can run on a 24 GB GPU?
- Qwen3.8 27B is the highest-scoring open model that fits in 24 GB at 4-bit quantization (~17 GB), scoring 75.7 on LiveBench Coding.
- Can open models match proprietary models on LiveBench Coding?
- Not quite on LiveBench Coding: the strongest proprietary model (Claude Sonnet 5.5 Max) scores 91.4, ahead of the best open model (Kimi K3) at 81.5 — but you can run the open one yourself.
Scores aggregated from livebench. llmrun does not run this benchmark — see the source for methodology, or the about benchmarks for what it measures.