Coding Leaderboard

Models ranked by Coding Index, based on independent benchmark evaluations.

Each row shows the model's benchmark score alongside its pricing and output speed, so you can evaluate quality-to-cost tradeoffs at a glance.

Top 20 models ranked by coding index

Rank	Model	Creator	Coding Index	Price/1M	Speed
🥇	Anthropic: Claude Fable 5 Anthropic	Anthropic	76.5	$20.00	77 tok/s
🥈	OpenAI: GPT-5.5 OpenAI	OpenAI	74.9	$11.25	82 tok/s
🥉	Anthropic: Claude Opus 4.8 Anthropic	Anthropic	74.3	$10.00	58 tok/s
4	Anthropic: Claude Opus 4.7 Anthropic	Anthropic	73.6	$10.00	51 tok/s
5	GPT-5.5 (high) OpenAI	OpenAI	71.6	$11.25	83 tok/s
6	GPT-5.5 (medium) OpenAI	OpenAI	71.5	$11.25	71 tok/s
7	OpenAI: GPT-5.4 OpenAI	OpenAI	71.1	$5.63	166 tok/s
8	Google: Gemini 3.5 Flash Google	Google	70.1	$3.38	210 tok/s
9	Z.ai: GLM 5.2 Z AI	Z AI	68.8	$1.46	135 tok/s
10	Google: Gemini 3.1 Pro Preview Google	Google	68.8	$4.50	141 tok/s
11	Qwen: Qwen3.7 Max Alibaba	Alibaba	66.0	$1.88	196 tok/s
12	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) Anthropic	Anthropic	63.0	$6.00	63 tok/s
13	GPT-5.5 (low) OpenAI	OpenAI	60.9	$11.25	70 tok/s
14	MoonshotAI: Kimi K2.7 Code Kimi	Kimi	60.8	$1.43	52 tok/s
15	Xiaomi: MiMo-V2.5-Pro Xiaomi	Xiaomi	60.2	$0.54	46 tok/s
16	DeepSeek: DeepSeek V4 Pro DeepSeek	DeepSeek	59.4	$0.54	84 tok/s
17	Nex AGI: Nex-N2-Pro Nex Agi	Nex Agi	59.1	$0.44	86 tok/s
18	KAT-Coder-Pro V1 KwaiKAT	KwaiKAT	58.9	$0.53	109 tok/s
19	MiniMax: MiniMax M3 MiniMax	MiniMax	58.6	$0.52	85 tok/s
20	Muse Spark Meta	Meta	58.6	N/A	—