Code Arena🏆WebDev

View overall rankings across AI models on agentic coding tasks involving multi-step reasoning and tool use.

Apr 14, 2026

235,275 votes

60 models

	Rank Spread
1	13	claude-opus-4-6-thinking Anthropic · Proprietary	1548+11/-11	4,237	$5 / $25	1M
2	13	claude-opus-4-6 Anthropic · Proprietary	1545+10/-10	5,085	$5 / $25	1M
3	14	glm-5.1 Z.ai · MIT	1537+17/-17	1,482	$0.95 / $3.15	202.8K
4	34	claude-sonnet-4-6 Anthropic · Proprietary	1524+9/-9	7,077	$3 / $15	1M
5	55	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1490+7/-7	13,065	$5 / $25	200K
6	69	claude-opus-4-5-20251101 Anthropic · Proprietary	1468+7/-7	14,690	$5 / $25	200K
7	615	gpt-5.4-high (codex-harness) OpenAI · Proprietary	1457+17/-17	1,483	$2.50 / $15	1.1M
8	613	gemini-3.1-pro-preview Google · Proprietary	1454+9/-9	6,069	$2 / $12	1M
9	615	qwen3.6-plus-preview Alibaba · Proprietary	1453+13/-13	2,211	$0.33 / $1.95	1M
10	717	glm-5 Z.ai · MIT	1440+9/-9	4,959	$1 / $3.20	202.8K
11	717	glm-4.7 Z.ai · MIT	1440+10/-10	4,878	$0.39 / $1.75	202.8K
12	717	gemini-3-pro Google · Proprietary	1438+7/-7	17,162	$2 / $12	1M
13	717	gpt-5.4-medium (codex-harness) OpenAI · Proprietary	1437+16/-16	1,449	$2.50 / $15	1.1M
14	817	gemini-3-flash Google · Proprietary	1437+7/-7	13,269	$0.50 / $3	1M
15	817	mimo-v2-pro Xiaomi · Proprietary	1432+11/-11	3,234	$1 / $3	1M
16	1017	kimi-k2.5-thinking Moonshot · Modified MIT	1429+8/-8	7,339	$0.60 / $3	N/A
17	1020	minimax-m2.7 MiniMax · Modified MIT	1422+11/-11	3,026	$0.30 / $1.20	196.6K
18	1726	kimi-k2.5-instant Moonshot · Modified MIT	1408+11/-11	3,610	$0.38 / $1.72	262.1K
19	1728	gpt-5.3-codex (codex-harness) OpenAI · Proprietary	1407+12/-12	2,971	$1.75 / $14	400K
20	1731	gpt-5.2 OpenAI · Proprietary	1404+17/-17	1,461	$1.75 / $14	400K
21	1831	grok-4.20-beta-0309-reasoning xAI · Proprietary	1396+11/-11	3,378	$2 / $6	2M
22	1831	gpt-5.4-mini-high OpenAI · Proprietary	1393+15/-15	1,843	$2.50 / $15	1.1M
23	1831	gpt-5-medium OpenAI · Proprietary	1393+13/-13	3,755	$1.25 / $10	400K
24	1831	minimax-m2.1-preview MiniMax · MIT	1392+8/-8	9,273	$0.29 / $0.95	196.6K
25	1831	gpt-5.1-medium OpenAI · Proprietary	1391+9/-9	6,124	$1.25 / $10	400K
26	1831	qwen3.5-397b-a17b Alibaba · Apache 2.0	1389+8/-8	5,978	$0.39 / $2.34	262.1K
27	1931	gemini-3-flash (thinking-minimal) Google · Proprietary	1389+7/-7	12,677	$0.50 / $3	1M
28	1931	minimax-m2.5 MiniMax · Modified MIT	1388+8/-8	7,184	$0.12 / $0.99	196.6K
29	2031	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1388+6/-6	15,750	$3 / $15	200K
30	2031	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1386+6/-6	18,409	$3 / $15	200K
31	2032	claude-opus-4-1-20250805 Anthropic · Proprietary	1385+9/-9	8,573	$15 / $75	200K
32	3134	deepseek-v3.2-thinking DeepSeek · MIT	1368+8/-8	7,910	$0.26 / $0.38	163.8K
33	3235	qwen3.5-122b-a10b Alibaba · Apache 2.0	1364+9/-9	4,758	$0.26 / $2.08	262.1K
34	3236	glm-4.6 Z.ai · MIT	1354+9/-9	8,351	$0.39 / $1.90	204.8K
35	3340	qwen3.5-27b Alibaba · Apache 2.0	1347+10/-10	4,369	$0.20 / $1.56	262.1K
36	3441	gpt-5.1 OpenAI · Proprietary	1339+7/-7	12,875	$1.25 / $10	400K
37	3541	mimo-v2-flash (non-thinking) Xiaomi · MIT	1337+8/-8	6,734	$0.09 / $0.29	262.1K
38	3541	gpt-5.2-codex OpenAI · Proprietary	1335+8/-8	7,765	$1.75 / $14	400K
39	3541	deepseek-v3.2 DeepSeek · MIT	1330+7/-7	9,997	$0.26 / $0.38	163.8K
40	3641	kimi-k2-thinking-turbo Moonshot · Modified MIT	1330+6/-6	15,368	$1.15 / $8	262.1K
41	3542	gpt-5.1-codex OpenAI · Proprietary	1329+9/-9	6,229	$1.25 / $10	400K
42	4144	claude-haiku-4-5-20251001 Anthropic · Proprietary	1314+6/-6	17,091	$1 / $5	200K
43	4245	minimax-m2 MiniMax · Apache 2.0	1304+9/-9	8,402	$0.26 / $1	196.6K
44	4246	mimo-v2-flash (thinking) Xiaomi · MIT	1300+14/-14	2,095	$0.09 / $0.29	262.1K
45	4346	deepseek-v3.2-exp DeepSeek · MIT	1286+11/-11	4,870	$0.27 / $0.41	163.8K
46	4446	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1281+7/-7	15,212	$0.40 / $1.60	262.1K
47	4752	KAT-Coder-Pro-V1 KwaiKAT · Proprietary	1258+15/-15	1,883	$0.21 / $0.83	256K
48	4753	qwen3.5-35b-a3b Alibaba · Apache 2.0	1247+16/-16	1,817	$0.16 / $1.30	262.1K
49	4754	gpt-5.1-codex-mini OpenAI · Proprietary	1239+17/-17	1,444	$0.25 / $2	400K
50	4754	qwen3.5-flash Alibaba · Proprietary	1236+17/-17	1,562	N/A	N/A
51	4754	gemini-3.1-flash-lite-preview Google · Proprietary	1236+10/-10	5,544	$0.25 / $1.50	1M
52	4754	grok-4-1-fast-reasoning xAI · Proprietary	1234+9/-9	6,916	$0.20 / $0.50	2M
53	4856	mistral-large-3 Mistral · Apache 2.0	1222+20/-20	1,032	$0.50 / $1.50	N/A
54	4957	grok-4.1-thinking xAI · Proprietary	1207+20/-20	1,209	N/A	N/A
55	5357	gemini-2.5-pro Google · Proprietary	1202+13/-13	3,300	$1.25 / $10	1M
56	5357	devstral-2 Mistral · Modified MIT	1199+17/-17	1,579	N/A	N/A
57	5459	mercury-2 Inception AI · Proprietary	1167+23/-23	951	$0.25 / $0.75	128K
58	5759	grok-4-fast-reasoning xAI · Proprietary	1148+23/-23	936	$0.20 / $0.50	2M
59	5759	grok-code-fast-1 xAI · Proprietary	1139+22/-22	984	$0.20 / $1.50	256K
60	6060	devstral-medium-2507 Mistral · Proprietary	1091+23/-23	993	$0.40 / $2	128K

Code Arena🏆WebDev

Remove Style Control Leaderboard Plots

Fraction of Model A Wins for All Non-tied A vs. B Battles

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)