New: Agent Index for knowledge work is live.Explore the index ↗

Best LLMs for solving coding problems

LiveBench: Coding

LiveBench 2.0 evaluates coding with LiveBench on its October 25, 2026 release. This suite contains 29 tasks or questions, scored from 0 to 100 in one run per model. Models use their highest supported effort unless a different setting is reported. This is an individual task-suite score, separate from LiveBench’s weighted overall average.

Updated: Nov 5, 2026Data as of: Nov 2, 2026

Widely usedNot saturated

Official benchmark

LiveBench: Coding results. Each row identifies its benchmark version and evaluation track. Scores from different versions are not directly comparable. Best effort from the latest stored report date per model and version.
Model / creator	Version	Reported score
Claude Fable 5.1Anthropic · Proprietary	2.0 / 2026-10-25	97.7%
Claude Opus 5.5Anthropic · Proprietary	2.0 / 2026-10-25	96.3%
DeepSeek V4.1 Flash 1017DeepSeek · Open source / open weights	2.0 / 2026-10-25	96%
GPT-6.1 SolOpenAI · Proprietary	2.0 / 2026-10-25	96%
Claude Sonnet 5.5Anthropic · Proprietary	2.0 / 2026-10-25	94.7%
GPT-6.1 TerraOpenAI · Proprietary	2.0 / 2026-10-25	94.3%
GPT-6 AstraOpenAI · Proprietary	2.0 / 2026-10-25	93.7%
Claude Haiku 5.5Anthropic · Proprietary	2.0 / 2026-10-25	91.4%
Muse Spark 1.3Meta · Proprietary	2.0 / 2026-10-25	90.2%
Gemini 4 ArgonGoogle · Proprietary	2.0 / 2026-10-25	89.7%
Qwen3.8 27BQwen · Open source / open weights	2.0 / 2026-10-25	86.8%
GPT-5.6 TerraOpenAI · Proprietary	2.0 / 2026-10-25	86.2%
Muse Wonder 1.0Meta · Proprietary	2.0 / 2026-10-25	86.2%
Step 5 PreviewStepFun · Open source / open weights	2.0 / 2026-10-25	85.6%
GPT-6 LunaOpenAI · Proprietary	2.0 / 2026-10-25	84.5%
Grok 4.7xAI · Proprietary	2.0 / 2026-10-25	84.5%
MiniMax M3.1 FlashMiniMax · Open source / open weights	2.0 / 2026-10-25	83.9%
GLM-5.3Z.ai · Open source / open weights	2.0 / 2026-10-14	82.8%
Gemini 3.8 FlashGoogle · Proprietary	2.0 / 2026-10-25	82.2%
Kimi K3.1 ProMoonshot AI · Open source / open weights	2.0 / 2026-10-25	81.8%
MiMo-V2.6-ProXiaomi · Open source / open weights	2.0 / 2026-10-25	81.5%
GLM-5.3-FlashZ.ai · Open source / open weights	2.0 / 2026-10-25	80.6%
Muse Spark OpenMeta · Open source / open weights	2.0 / 2026-10-25	73.6%
Nemotron 3.5 Super VLNVIDIA · Open source / open weights	2.0 / 2026-10-25	71.3%
InklingThinking Machines · Open source / open weights	2.0 / 2026-10-25	64%
Kimi K3Moonshot AI · Open source / open weights	2.0 / 2026-10-25	59.3%

View all 26 published reports

GPT-6.1 Terra94.3%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Claude Haiku 5.591.4%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Qwen3.8 27B86.8%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Muse Wonder 1.086.2%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

GPT-5.6 Terra86.2%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Step 5 Preview85.6%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

GPT-6 Luna84.5%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

MiMo-V2.6-Pro81.5%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Muse Spark Open73.6%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Nemotron 3.5 Super VL71.3%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Claude Fable 5.197.7%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Claude Opus 5.596.3%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

DeepSeek V4.1 Flash 101796%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Claude Sonnet 5.594.7%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

GPT-6 Astra93.7%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Muse Spark 1.390.2%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Gemini 4 Argon89.7%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

MiniMax M3.1 Flash83.9%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Gemini 3.8 Flash82.2%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

Kimi K3.1 Pro81.8%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

GLM-5.3-Flash80.6%

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

2.0 / 2026-10-25

release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding

2.0 / 2026-10-14

release: 2026-10-14 · Official LiveBench 2.0 row GLM-5.3. One run per suite; effort not explicitly labeled on this row. Historical release, not the October 25 index track. · source model id: glm-5.3 · suite: coding