Best LLM for coding
Looking for the best LLM for coding? These rankings compare models on writing new code, fixing bugs and working across large codebases.
#1 for CodingAnthropic
Claude Fable 5.1
Claude Fable 5.1 has the highest Artificial Analysis Coding Index of the models we track — an independent test of writing and fixing real code.
See the full breakdown1
Claude Fable 5.1
Anthropic
Input
$10.00
Output
$50.00
Context
1M
100.0
2GPT-6 Astra
OpenAI
Input
$10.00
Output
$50.00
Context
1M
94.2
3Gemini 3.8 Flash
Google DeepMind
Input
$0.75
Output
$3.75
Context
1M
93.5
4Qwen3.8 Max
Alibaba Qwen
Input
$2.00
Output
$6.00
Context
984K
93.4
5Kimi K3
Moonshot AI
Input
$3.00
Output
$15.00
Context
1.1M
93.4
6Muse Spark 1.3
Meta
Input
$1.25
Output
$4.25
Context
1M
92.9
7GLM-5.3
z.ai
Input
$1.40
Output
$4.40
Context
1M
91.7
8DeepSeek V4 Pro
DeepSeek
Input
$1.32
Output
$3.96
Context
1M
84.3
9MiniMax-M3
MiniMax
Input
$0.30
Output
$1.20
Context
1M
71.8
10Mistral Medium 3.5
Mistral AI
Input
$1.50
Output
$7.50
Context
—
57.5
Get the weekly LLM rankings
One email a week: what moved, what's new, and which model to actually use for your work. No hype, no benchmark jargon.