Best AI model for writing & editing code (2026-09)

Most capable

Claude Opus 4.6

Anthropic

$10.00 / 1M blended

100% of leader strength

anthropic/claude-opus-4.6

Best value

GLM 5.3 Flash

Z.ai (Zhipu)

$0.24 / 1M blended

95% of leader strength · 98% cheaper

z-ai/glm-5.3-flash

Budget

DeepSeek V4 Flash 0731

DeepSeek

$0.10 / 1M blended

78% of leader strength · 99% cheaper

deepseek/deepseek-v4-flash-0731

Best for agents

GLM 5.3 Flash

Z.ai (Zhipu)

$0.24 / 1M blended

95% of leader strength · 98% cheaper

z-ai/glm-5.3-flash

Top 25 models for writing & editing code

Rows marked frontier are Pareto-optimal — nothing we track is both stronger and cheaper. "Strength" rescales the board so 100% = parity with the leader.

#	Model	Provider	Score	Strength	$/1M	Context	Tools
1	Claude Opus 4.6 `anthropic/claude-opus-4.6`	Anthropic	1534	100%	$10.00	1M	tools
2	Claude Opus 5 `anthropic/claude-opus-5`	Anthropic	1532	99%	$10.00	1M	tools
3	Claude Fable 5 `anthropic/claude-fable-5`	Anthropic	1519	96%	$20.00	1M	tools
4	GLM 5.3 Flash `z-ai/glm-5.3-flash`	Z.ai (Zhipu)	1516	95%	$0.24	1.31072M	tools
5	Gemini 3.8 Flash `google/gemini-3.8-flash`	Google	1516	95%	$1.50	1.048576M	tools
6	Claude Opus 4.7 `anthropic/claude-opus-4.7`	Anthropic	1516	95%	$10.00	1M	tools
7	Kimi K3 `moonshotai/kimi-k3`	Moonshot AI	1511	93%	$6.00	1.048576M	tools
8	Claude Fable 5.1 `anthropic/claude-fable-5.1`	Anthropic	1508	93%	$20.00	1M	tools
9	Gemini 3.7 Flash `google/gemini-3.7-flash`	Google	1504	91%	$1.50	1.048576M	tools
10	Claude Sonnet 4.6 `anthropic/claude-sonnet-4.6`	Anthropic	1504	91%	$6.00	1M	tools
11	GLM 5.3 `z-ai/glm-5.3`	Z.ai (Zhipu)	1503	91%	$2.15	1.31072M	tools
12	Qwen3.8 Max (0902) `qwen/qwen3.8-max-0902`	Qwen (Alibaba)	1498	90%	$3.00	1M	tools
13	Qwen3.7 Max `qwen/qwen3.7-max`	Qwen (Alibaba)	1498	90%	$2.21	1M	tools
14	Gemini 3.5 Flash `google/gemini-3.5-flash`	Google	1493	88%	$3.38	1.048576M	tools
15	Gemini 3.6 Flash `google/gemini-3.6-flash`	Google	1492	88%	$1.50	1.048576M	tools
16	GPT-5.6 Sol `openai/gpt-5.6-sol`	OpenAI	1490	88%	$4.00	1.05M	tools
17	GLM 5.1 `z-ai/glm-5.1`	Z.ai (Zhipu)	1487	86%	$1.49	205K	tools
18	GPT-5.6 Terra `openai/gpt-5.6-terra`	OpenAI	1487	86%	$4.50	1.05M	tools
19	Kimi K2.6 `moonshotai/kimi-k2.6`	Moonshot AI	1487	86%	$1.71	262K	tools
20	Claude Sonnet 5 `anthropic/claude-sonnet-5`	Anthropic	1485	86%	$4.00	1M	tools
21	Kimi K2.5 `moonshotai/kimi-k2.5`	Moonshot AI	1485	86%	$0.90	262K	tools
22	Claude Opus 4.8 `anthropic/claude-opus-4.8`	Anthropic	1485	86%	$10.00	1M	tools
23	Grok 4.5 `x-ai/grok-4.5`	xAI	1483	85%	$3.00	500K	tools
24	GLM 5.2 `z-ai/glm-5.2`	Z.ai (Zhipu)	1479	84%	$1.49	1.048576M	tools
25	Qwen3.8 27B `qwen/qwen3.8-27b`	Qwen (Alibaba)	1477	84%	$1.06	1M	tools

Capability: Arena leaderboard dataset (CC-BY-4.0), Arena text / coding, published 2026-09-02. Pricing: OpenRouter, retrieved 2026-09-10. (input x 3 + output x 1) / 4.

What this measures: Human pairwise preference votes. Measures perceived answer quality on this category, not correctness on a fixed test set. For each model this is the probability it beats the board leader in a head-to-head human vote — 0.50 means a dead tie and is the best possible value.

Get this as JSON

curl -s https://agentleaderboards.com/api/v1/route/coding.json | jq .picks

No key, open CORS, refreshed daily. Set your own budget and constraints →

Other tasks

Autonomous agent work · Tool-call reliability · Following operator instructions · Recovering from shell errors · Hard reasoning · Mathematics · Precise instruction following · Long multi-turn chat · Long inputs · Creative writing · General assistant · Software & IT services · Legal & government · Medicine & healthcare · Science · Business & finance · Writing & language