Coding Models

Updated Oct 21, 2026

Which model writes the better working software, from real engineering tests and developers' side-by-side votes.

Best overall
Claude Opus 5.5 (Max) Anthropic

Highest ToolsGuide Score for coding

674 / 1,000
Best for React
Claude Sonnet 5.5 (xHigh) Anthropic

Top scored on React apps

683 / 1,000
Best value
Claude Haiku 5.5 (High) Anthropic

Lowest price in the top 20

$0.10 per 1M input tokens

Coding model leaderboard

147 models · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

20 of 147 models in the chart · ·

All models

#	Model	Creator	Licence	Input / 1M	Score	From votes	From tests · count	Votes
1	Claude Opus 5.5 (Max)	Anthropic	Proprietary	$4.00	674	672	675 · 6	2,925
2	Claude Sonnet 5.5 (xHigh)	Anthropic	Proprietary	$2.00	636	628	641 · 6	3,428
3	Claude Sonnet 5.5 (High)	Anthropic	Proprietary	$2.00	609	562	641 · 6	5,158
4	GPT-6 Astra (Max)	OpenAI	Proprietary	$10.00	604	635	584 · 3	6,169
5	Claude Fable 5.1 (Max)	Anthropic	Proprietary	$10.00	599	599	–	7,744
6	Claude Opus 5 (Max)	Anthropic	Proprietary	$5.00	552	538	561 · 3	18,555
7	Gemini 4 Argon (High)	Google	Proprietary	$2.00	549	527	583 · 2	1,728
8	Claude Opus 5 (High)	Anthropic	Proprietary	$5.00	538	506	561 · 3	24,739
9	Muse Wonder (Max)	Meta	Proprietary	$4.00	538	498	565 · 3	2,289
10	GPT-6.1 Sol (Max)	OpenAI	Proprietary	$2.00	536	611	435 · 2	3,072
11	Claude Fable 5 (High)	Anthropic	Proprietary	$10.00	526	471	564 · 7	15,899
12	Muse Wonder Full (Max)	Meta	Proprietary	–	525	580	449 · 2	1,639
13	DeepSeek-V4.1-Flash-20261017 (Max)	DeepSeek	MIT	–	512	512	–	2,008
14	Kimi K3 (Max)	Moonshot AI	Kimi K3 license	$2.85	511	502	517 · 6	19,592
15	GPT-5.6 Sol (xHigh, Codex Harness)	OpenAI	Proprietary	$5.00	505	462	535 · 6	17,786
16	Grok 4.7 (xHigh)	xAI	Proprietary	$2.00	496	483	516 · 2	5,303
17	Claude Haiku 5.5 (High)	Anthropic	Proprietary	$0.10	495	434	540 · 5	3,514
18	GLM-5.3 (Max)	Z.ai	MIT	$1.20	489	468	503 · 6	9,828
19	MiMo-V2.6-Pro	Xiaomi	MIT	$0.43	488	471	500 · 4	5,041
20	MiniMax-M3.1-Flash	MiniMax	MiniMax Community License	$0.15	485	435	521 · 3	1,853
21	Muse Spark 1.3 (Max)	Meta	Proprietary	$0.10	482	507	447 · 2	9,407
22	GPT-6 Sol (Max)	OpenAI	Proprietary	$2.00	482	532	413 · 2	4,608
23	MiMo-V2.6-Flash	Xiaomi	MIT	$0.14	477	480	474 · 4	5,293
24	Qwen3.8-Max (0902)	Alibaba	Proprietary	$1.65	472	523	440 · 5	14,421
25	Qwen3.8-Max	Alibaba	Proprietary	$1.65	471	520	440 · 5	3,428
26	DeepSeek-V4.1-Flash-20260910 (Max)	DeepSeek	MIT	–	465	465	–	3,528
27	Mistral Large 4	Mistral	Proprietary	$0.68	460	394	508 · 3	2,832
28	Muse Spark 1.3 (xHigh)	Meta	Proprietary	$0.10	459	468	447 · 2	8,767
29	Grok 4.6 (High)	xAI	Proprietary	$2.00	458	463	452 · 2	10,483
30	Gemini 3.8 Flash (High)	Google	Proprietary	$0.75	457	432	473 · 3	10,851
31	Hy4 preview	Tencent	Apache 2.0	–	449	477	430 · 7	4,798
32	GPT-5.6 Terra (xHigh, Codex Harness)	OpenAI	Proprietary	$2.00	442	377	491 · 6	13,919
33	Claude Opus 4.8 (High)	Anthropic	Proprietary	$5.00	438	406	460 · 9	18,493
34	GLM-5.2 (Max)	Z.ai	MIT	$0.75	433	451	422 · 9	16,657
35	Claude Opus 4.8	Anthropic	Proprietary	$5.00	431	389	460 · 9	17,398
36	Gemini 3.7 Flash (High)	Google	Proprietary	$0.75	430	438	425 · 3	12,636
37	DeepSeek-V4-Pro (High, 20260813)	DeepSeek	MIT	–	430	430	–	4,714
38	DeepSeek-V4-Flash (High)	DeepSeek	MIT	–	430	430	–	4,947
39	GPT-5.6 Luna (xHigh, Codex Harness)	OpenAI	Proprietary	$0.20	430	374	470 · 6	12,501
40	GLM-5.3-Flash	Z.ai	MIT	$0.15	423	453	404 · 3	18,264
41	Grok 4.5	xAI	Proprietary	$2.00	421	404	433 · 6	11,082
42	Step 5 Preview (High)	Stepfun	Proprietary	–	416	416	–	4,728
43	GPT-6 Luna (Max)	OpenAI	Proprietary	$0.10	412	426	392 · 2	21,622
44	GPT-5.5 (xHigh, Codex Harness)	OpenAI	Proprietary	$5.00	408	369	435 · 6	15,612
45	Claude Sonnet 5 (High)	Anthropic	Proprietary	$2.00	403	393	411 · 7	15,755
46	Qwen3.8-Flash-Next	Alibaba	qwen-community-1.0	–	403	475	359 · 4	8,382
47	GPT-5.5 (High, Codex Harness)	OpenAI	Proprietary	$5.00	399	348	435 · 6	17,939
48	Claude Opus 4.7 (High)	Anthropic	Proprietary	$5.00	396	408	389 · 6	17,910
49	Claude Opus 4.7	Anthropic	Proprietary	$5.00	396	406	389 · 6	18,230
50	Muse Spark 1.1	Meta	Proprietary	$1.25	392	394	391 · 4	7,985
51	GPT-5.5 (Codex Harness)	OpenAI	Proprietary	$5.00	388	324	435 · 6	15,860
52	Muse Spark Open (Max)	Meta	muse-model-license	$1.25	386	382	389 · 4	1,380
53	Muse Spark 1.2 (xHigh)	Meta	Proprietary	$0.10	384	387	380 · 2	2,163
54	Seed2.1 Pro Preview	ByteDance	Proprietary	–	375	375	–	15,123
55	Qwen3.8-27B	Alibaba	Apache 2.0	$0.40	369	440	326 · 4	16,385
56	Gemini 3.6 Flash (High)	Google	Proprietary	$1.50	363	390	345 · 3	8,762
57	Claude Opus 4.6 (High)	Anthropic	Proprietary	$5.00	363	398	340 · 5	19,383
58	Claude Opus 4.6	Anthropic	Proprietary	$5.00	360	390	340 · 5	20,644
59	Gemini 3.5 Flash (High)	Google	Proprietary	$1.50	352	358	347 · 4	9,382
60	Gemini 3.5 Flash (Medium)	Google	Proprietary	$1.50	349	351	347 · 4	12,137
61	GPT-5.4 (High, Codex Harness)	OpenAI	Proprietary	$2.50	348	330	360 · 5	1,350
62	Hy3	Tencent	Apache 2.0	$0.14	347	364	335 · 8	6,256
63	Qwen3.7-Max (20260517)	Alibaba	Proprietary	$1.25	345	371	328 · 8	8,887
64	Qwen3.6-Max-Preview	Alibaba	Proprietary	–	344	344	–	2,708
65	Kimi K2.6	Moonshot AI	Modified MIT	$0.75	343	366	328 · 7	10,166
66	GPT-5.4 (Medium, Codex Harness)	OpenAI	Proprietary	$2.50	341	315	360 · 5	1,380
67	Kimi K2.7 Code	Moonshot AI	Modified MIT	$0.68	337	337	336 · 4	4,962
68	GLM-5.1	Z.ai	MIT	$1.05	335	365	316 · 5	10,703
69	DeepSeek-V4-Pro Preview (High)	DeepSeek	MIT	–	330	330	–	13,161
70	MiniMax-M3	MiniMax	MiniMax Community License	$0.28	330	344	321 · 7	19,803
71	GPT-5.4	OpenAI	Proprietary	$2.50	328	283	360 · 5	4,130
72	MiMo-V2.5-Pro	Xiaomi	MIT	$0.43	323	343	310 · 4	22,493
73	DeepSeek-V4-Pro	DeepSeek	MIT	–	317	317	–	13,979
74	Claude Sonnet 4.6	Anthropic	Proprietary	$3.00	316	378	279 · 4	22,822
75	Claude Opus 4.5 (High, 32K, 20251101)	Anthropic	Proprietary	–	315	353	290 · 3	11,029
76	beam-1.0-501b-a23b	Reflection	Apache 2.0	–	309	309	–	2,930
77	MiMo-V2.5	Xiaomi	MIT	$0.17	308	311	306 · 3	14,910
78	Qwen3.6-Plus	Alibaba	Proprietary	$0.50	307	328	294 · 8	18,587
79	Claude Opus 4.5 (20251101)	Anthropic	Proprietary	–	307	334	290 · 3	13,418
79	Gemini 3.1 Pro Preview	Google	Proprietary	$2.00	307	317	301 · 7	24,199
80	DeepSeek-V4-Flash Preview (High)	DeepSeek	MIT	–	305	305	–	10,105
81	Inkling-Small	Thinky	Apache 2.0	$0.30	303	290	313 · 5	5,323
82	Inkling	Thinky	Apache 2.0	$0.95	299	293	304 · 3	15,778
83	MiMo-V2-Pro	Xiaomi	Proprietary	–	299	307	293 · 4	7,249
84	Gemini 3 Pro	Google	Proprietary	–	297	312	276 · 2	14,092
85	GLM-5	Z.ai	MIT	$1.00	295	308	286 · 3	7,496
86	GPT-5.3-Codex (Codex Harness)	OpenAI	Proprietary	$1.75	293	263	341 · 2	2,641
87	Kimi K2.5 (Thinking)	Moonshot AI	Modified MIT	–	292	309	281 · 6	20,091
88	MiniMax-M2.7	MiniMax	Modified MIT	$0.30	292	282	299 · 4	15,972
89	Gemini 3.5 Flash-Lite	Google	Proprietary	$0.30	291	308	268 · 2	238
90	GPT-5.2	OpenAI	Proprietary	$1.75	288	295	279 · 2	1,081
91	NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)	NVIDIA	OpenMDW-1.1	–	286	286	–	1,843
92	GLM-5V-Turbo	Z.ai	Proprietary	–	284	284	–	2,403
93	GPT-5 (Medium)	OpenAI	Proprietary	–	284	295	276 · 3	3,092
94	Kimi K2.5 (Instant)	Moonshot AI	Modified MIT	–	283	287	281 · 6	3,264
95	Gemini 3 Flash	Google	Proprietary	$0.50	282	312	263 · 3	10,889
96	MiniMax-M2.5	MiniMax	Modified MIT	$0.30	281	274	292 · 2	7,621
97	GPT-5.1 (Medium)	OpenAI	Proprietary	$1.25	280	280	–	4,910
98	Claude Sonnet 4.5 (High, 32K, 20250929)	Anthropic	Proprietary	$3.00	279	279	–	13,250
98	Qwen3.5-397B-A17B	Alibaba	Apache 2.0	$0.45	279	283	276 · 3	21,156
99	GPT-5.4 mini (High)	OpenAI	Proprietary	$0.75	278	281	276 · 3	11,942
100	Claude Sonnet 4.5 (20250929)	Anthropic	Proprietary	$3.00	273	273	–	15,722
101	MiniMax-M2.1 Preview	MiniMax	MIT	–	272	272	–	7,638
102	Gemini 3 Flash (Minimal)	Google	Proprietary	$0.50	267	273	263 · 3	22,154
103	Grok 4.20 Beta (Reasoning, 0309)	xAI	Proprietary	–	266	266	–	15,448
104	GPT-5.2-Codex	OpenAI	Proprietary	$1.75	265	243	301 · 2	6,718
105	Claude Opus 4.1 (20250805)	Anthropic	Proprietary	–	263	276	244 · 2	6,927
106	Gemma 4 31B	Google	Apache 2.0	$0.09	261	261	–	14,666
107	Solar Pro 4	Upstage	Proprietary	$0.30	259	263	257 · 3	4,655
108	GLM-4.7	Z.ai	MIT	$0.40	259	308	229 · 4	4,007
109	DeepSeek-V3.2 (Thinking)	DeepSeek	MIT	$0.28	258	258	–	6,914
110	Qwen3.5-122B-A10B	Alibaba	Apache 2.0	$0.29	258	256	259 · 2	8,235
111	Gemma 4 26B A4B	Google	Apache 2.0	$0.07	256	256	–	1,501
112	Grok 4.3	xAI	Proprietary	$1.25	255	255	–	14,954
113	Hy3 preview	Tencent	tencent-hunyuan-community	–	254	254	–	1,448
114	Muse Glimmer	Meta	Apache-2.0	–	253	253	–	1,643
115	Qwen3.5-27B	Alibaba	Apache 2.0	$0.26	252	255	248 · 2	7,782
116	GPT-5.1-Codex	OpenAI	Proprietary	–	252	242	268 · 2	5,007
117	Laguna M.1	Poolside	Apache 2.0	–	250	250	–	5,395
118	GPT-5.1	OpenAI	Proprietary	$1.25	244	244	–	10,711
119	GLM-4.6	Z.ai	MIT	$0.50	239	244	232 · 2	6,781
120	Claude Haiku 4.5 (20251001)	Anthropic	Proprietary	$1.00	238	237	239 · 2	29,061
121	DeepSeek-V3.2	DeepSeek	MIT	$0.28	235	235	–	9,382
122	Kimi K2 Thinking Turbo	Moonshot AI	Modified MIT	–	232	232	–	13,092
123	MiMo-V2-Flash (Non-Thinking)	Xiaomi	MIT	–	231	237	226 · 4	5,689
124	MiniMax-M2	MiniMax	Apache 2.0	$0.30	227	217	233 · 5	6,714
125	MiMo-V2-Flash (Thinking)	Xiaomi	MIT	–	222	215	226 · 4	1,685
126	Laguna XS.2	Poolside	Apache 2.0	–	221	221	–	4,228
127	Qwen3.5-35B-A3B	Alibaba	Apache 2.0	$0.14	211	194	240 · 2	1,617
128	DeepSeek-V3.2-Exp	DeepSeek	MIT	–	210	203	215 · 5	3,969
129	Qwen3-Coder-480B-A35B-Instruct	Alibaba	Apache 2.0	$0.30	204	205	204 · 4	12,709
130	Mistral Medium 3.5	Mistral	Modified MIT	$1.50	199	199	–	2,317
131	Gemini 2.5 Pro	Google	Proprietary	$1.25	196	179	223 · 2	2,730
132	Gemini 3.1 Flash-Lite Preview	Google	Proprietary	$0.25	195	195	–	14,390
133	KAT-Coder-Pro V1	Unknown	Proprietary	–	195	195	–	1,504
134	GPT-5.1-Codex-Mini	OpenAI	Proprietary	–	188	188	–	1,154
134	Qwen3.5-Flash	Alibaba	Proprietary	–	188	188	–	1,328
135	Grok 4.1 Fast (Reasoning)	xAI	Proprietary	$0.20	187	187	–	5,489
136	Trinity Large Thinking	Unknown	Apache 2.0	–	185	185	–	1,361
137	Mistral Large 3	Mistral	Apache 2.0	$0.50	181	181	–	839
138	Grok 4.1 (Thinking)	xAI	Proprietary	–	174	174	–	961
139	Mercury 2	Inception	Proprietary	$0.25	171	153	201 · 2	954
140	Devstral 2	Mistral	Modified MIT	–	165	165	–	1,182
141	Granite 4.1 8B	IBM	Apache 2.0	–	163	163	–	1,768
142	Grok Code Fast 1	xAI	Proprietary	$0.20	151	151	–	789
143	Grok 4 Fast (Reasoning)	xAI	Proprietary	$0.20	148	148	–	742
144	Devstral Medium (2507)	Mistral	Proprietary	–	115	115	–	842

Leaders by app type

The top model for each kind of task, scored from votes on that task alone, and how many models were ranked.

Task	Leader	Score	Models ranked
HTML apps	GPT-6.1 Sol (Max) OpenAI	664	146
React apps	Claude Opus 5.5 (Max) Anthropic	722	131
Screenshot to web app	Claude Opus 5.5 (Max) Anthropic	610	64
Web apps	Claude Opus 5.5 (Max) Anthropic	672	147

Fixed tests with right and wrong answers, scored out of 100%.

SWE-Bench Verified

Fixing real bugs in real GitHub projects, checked by the projects' own tests. · Top 10 of 120 · Higher is better

SWE-Bench Pro

Harder, longer software engineering tasks from real codebases. · Top 10 of 61 · Higher is better

Terminal-Bench 2.0

Getting real work done in a command-line terminal. · Top 10 of 54 · Higher is better

Coding model leaderboard

Leaders by app type

Related benchmarks