benchmark evidence
LiveBench Coding
LiveBench coding benchmark.
winner on LiveBench Coding
direct benchmark result, not a broad vertical composite | source row dated 2026-05-20
scored on 2026-05-20
latest mapped results | top 20
| # | Model | Score | Evidence | Tested |
|---|---|---|---|---|
| 1 | DeepSeek: DeepSeek V3.2 | 71.1 | model-only independent_benchmark | 2026-05-20 |
| 2 | DeepSeek: R1 | 70.3 | model-only independent_benchmark | 2026-05-20 |
| 3 | OpenAI: o3 Mini | 69.5 | model-only independent_benchmark | 2026-05-20 |
| 4 | Google: Gemini 2.5 Pro | 63.3 | model-only independent_benchmark | 2026-05-20 |
| 5 | Qwen2.5 Coder 32B Instruct | 57.0 | model-only independent_benchmark | 2026-05-20 |
| 6 | Google: Gemini 2.0 Flash | 54.7 | model-only independent_benchmark | 2026-05-20 |
| 7 | OpenAI: o1 | 52.3 | model-only independent_benchmark | 2026-05-20 |
| 8 | Meta: Llama 4 Maverick | 51.1 | model-only independent_benchmark | 2026-05-20 |
| 9 | Mistral Large | 46.9 | model-only independent_benchmark | 2026-05-20 |
| 10 | OpenAI: GPT-5 | 46.1 | model-only independent_benchmark | 2026-05-20 |
| 11 | DeepSeek: DeepSeek V4 Pro | 44.4 | model-only independent_benchmark | 2026-05-08 |
| 12 | Google: Gemini 2.0 Flash Lite | 43.8 | model-only independent_benchmark | 2026-05-20 |
| 13 | Google: Gemma 3 27B | 39.8 | model-only independent_benchmark | 2026-05-20 |
| 14 | Amazon: Nova Pro 1.0 | 39.1 | model-only independent_benchmark | 2026-05-20 |
| 15 | Mistral: Mistral Small 4 | 36.7 | model-only independent_benchmark | 2026-05-20 |
| 16 | Meta: Llama 3.3 70B Instruct | 20.0 | model-only independent_benchmark | 2026-05-20 |
what this result means
LiveBench coding benchmark.
This benchmark contributes direct public evidence. Read its scope before generalizing the result.
A win here is a win on LiveBench Coding. Broad task pages require independent corroboration before naming a general winner.
source record
category: coding
metric: accuracy
matched models: 16
latest source date: 2026-05-20
direction: higher is better