Best LLMs for Coding — 2026 Rankings

Coding LLM Leaderboard

Which AI model writes the best code? We rank every major LLM — open and closed source — across software engineering, code generation, competitive programming, and agentic coding benchmarks.

Roshan Desai

Roshan Desai · Last updated: 2026-07-20

LLM Leaderboard (All Models)

→

Open Source LLM Leaderboard

→

Self-Hosted LLM Leaderboard

→

S

Claude Fable 5

GPT-5.6 Sol

Kimi K3

2.8T

A

Claude Opus 4.8

GPT-5.5

DeepSeek-V4-Pro

1.6T

Kimi K2.6

1T

GLM-5.2

753B

GPT-5.6 Terra

Claude Sonnet 5

MiniMax M3

428B

DeepSeek-V4-Flash

284B

Step-3.7-Flash

198B

Qwen3.6-27B

27B

Gemini 3.1 Pro

N/A

GPT-5.6 Luna

B

Qwen3.6-35B-A3B

35B

DeepSeek V3.2

685B

DeepSeek R1

671B

MiMo-V2-Flash

309B

Step-3.5-Flash

196B

Qwen 3.5

397B

C

MiMo-V2.5-Pro

1.02T

GPT-oss 120B

117B

Nemotron Ultra 253B

253B

D

Llama 4 Maverick

400B

Grok 3

N/A

EnterpriseRAG-Bench · 500K+ docs · 9 enterprise sources · MIT
See how your RAG solution stacks up on real company data
See how we did it

Cost vs. Coding Performance

Which models give you the best coding performance for the price? Top-left is the sweet spot — high performance, low cost.

Top-left = best value (high performance, low cost). Models without pricing data are excluded.

Best Coding LLMs by Benchmark

How does each model perform on real-world software engineering, code generation, competitive programming, and terminal-based coding tasks? Hover any bar for details.

Best at Software Engineering

Real-world software engineering tasks (SWE-bench Verified)

Best for Code Generation

Python code generation from docstrings (HumanEval)

Best in Competitive Coding

Real-world coding problems (LiveCodeBench)

Best at Terminal Coding

Agentic terminal coding tasks (Terminal-Bench 2.1)

Hardest Software Engineering

Harder, contamination-resistant engineering tasks (SWE-bench Pro)

Coding Benchmark Scores & Pricing

Complete coding benchmark results and pricing for every model. Click any column header to sort.

Filter:

Claude Fable 5

Anthropic

1M

$10.00

$50.00

N/A

N/A

95.0

N/A

N/A

N/A

80.0

84.3

Claude Opus 4.8

Anthropic

1M

$5.00

$25.00

N/A

93.6

88.6

N/A

N/A

N/A

69.2

74.6

Claude Sonnet 5

Anthropic

1M

$2.00

$10.00

N/A

N/A

85.2

N/A

N/A

N/A

63.2

80.4

DeepSeek R1

DeepSeek

671B

128K

$0.28

$0.42

84.0

71.5

49.2

90.2

65.9

N/A

N/A

N/A

DeepSeek V3.2

DeepSeek

685B

130K

$0.28

$0.42

85.0

79.9

67.8

N/A

74.1

39.6

N/A

N/A

DeepSeek-V4-Flash

DeepSeek

284B

1M

$0.14

$0.28

86.2

88.1

79.0

N/A

91.6

56.9

N/A

N/A

DeepSeek-V4-Pro

DeepSeek

1.6T

1M

$0.43

$0.87

87.5

90.1

80.6

N/A

93.5

67.9

N/A

N/A

Gemini 3.1 Pro

Google

N/A

1M

$2.00

$12.00

85.0

91.9

78.0

93.0

81.3

56.2

N/A

N/A

GLM-5.2

Zhipu AI

753B

1M

$1.40

$4.40

N/A

91.2

N/A

N/A

N/A

N/A

N/A

81.0

GPT-5.5

OpenAI

1M

$5.00

$30.00

88.1

93.6

88.7

94.2

78.0

82.7

59.4

85.6

GPT-5.6 Luna

OpenAI

1M

$1.00

$6.00

N/A

92.3

N/A

N/A

N/A

N/A

62.7

84.7

GPT-5.6 Sol

OpenAI

1M

$5.00

$30.00

N/A

94.6

N/A

N/A

N/A

N/A

64.6

88.8

GPT-5.6 Terra

OpenAI

1M

$2.50

$15.00

N/A

92.9

N/A

N/A

N/A

N/A

63.4

87.4

GPT-oss 120B

OpenAI

117B

128K

N/A

N/A

90.0

80.9

62.4

88.3

60.0

18.7

N/A

N/A

Grok 3

xAI

N/A

131K

$3.00

$15.00

N/A

84.6

49.0

94.5

79.4

52.0

N/A

N/A

Kimi K2.6

Moonshot

1T

262K

$0.95

$4.00

N/A

90.5

80.2

N/A

89.6

66.7

N/A

N/A

Kimi K3

Moonshot

2.8T

1M

$3.00

$15.00

N/A

93.5

N/A

N/A

N/A

N/A

N/A

88.3

Llama 4 Maverick

Meta

400B

1M

N/A

N/A

80.5

69.8

N/A

62.0

43.4

N/A

N/A

N/A

MiMo-V2-Flash

Xiaomi

309B

262K

N/A

N/A

84.9

83.7

73.4

84.8

80.6

38.5

N/A

N/A

MiMo-V2.5-Pro

Xiaomi

1.02T

1M

$0.43

$0.87

68.5

66.7

N/A

N/A

39.6

N/A

N/A

N/A

MiniMax M3

MiniMax

428B

1M

$0.30

$1.20

N/A

N/A

80.5

N/A

N/A

N/A

59.0

N/A

Nemotron Ultra 253B

Nvidia

253B

128K

N/A

N/A

N/A

76.0

N/A

N/A

66.3

N/A

N/A

N/A

Qwen 3.5

Qwen

397B

262K

N/A

N/A

87.8

88.4

76.4

N/A

83.6

52.5

N/A

N/A

Qwen3.6-27B

Qwen

27B

262K

$0.60

$3.60

86.2

87.8

77.2

N/A

83.9

59.3

N/A

N/A

Qwen3.6-35B-A3B

Qwen

35B

262K

N/A

N/A

85.2

86.0

73.4

N/A

80.4

51.5

N/A

N/A

Step-3.5-Flash

Stepfun

196B

262K

$0.10

$0.30

85.8

N/A

74.4

81.1

86.4

51.0

N/A

N/A

Step-3.7-Flash

Stepfun

198B

262K

$0.20

$1.15

N/A

N/A

76.5

N/A

N/A

N/A

N/A

N/A

Compare Coding LLMs Head-to-Head

Select two models to see how they compare across all coding and reasoning benchmarks.

Model A

Model B

Claude Opus 4.8

GPT-5.5

GPQA Diamond

93.6

vs

93.6

SWE-bench Verified

88.6

vs

88.7

SWE-bench Pro

69.2

vs

59.4

Terminal-Bench 2.1

74.6

vs

85.6

Benchmarks won

1

vs

2

Try These Models in Onyx

Onyx is the open-source AI platform that lets you connect any of these LLMs to your team's docs, apps, and people.

Book a DemoView on GitHub
Best LLM for Coding 2026 | AI Coding Model Rankings & Benchmarks | Onyx AI