Best AI for Code in 2026Updated by AA Coding Index

Which AI codes best in 2026? Ranking of 480 models using AA Coding Index as the primary signal, with fallback to LiveCodeBench and SciCode. Built to favor current coding models instead of stale one-off spikes.

Synced: July 17, 2026 • 480 models with coding benchmarks

Use Cases

Code Autocomplete

Inline suggestions as you type. Ideal for IDEs like Cursor and VS Code.

Top models: GPT-5.6 Sol (xhigh), GPT-5.6 Sol (max), GPT-5.6 Sol (high)

Code Generation

Create functions, classes and full projects from natural language descriptions.

Top models: GPT-5.6 Sol (xhigh), GPT-5.6 Sol (max), GPT-5.6 Sol (high)

Debug & Code Review

Identify bugs, suggest fixes and review pull requests automatically.

Top models: GPT-5.6 Sol (xhigh), GPT-5.6 Sol (max), GPT-5.6 Sol (high)

Coding Ranking — Top Models

#ModelCompanyCoding ScoreBenchmarkContextInput PriceOpen Source
🥇GPT-5.6 Sol (xhigh)OpenAIOpenAI
78.3
AA Coding Index—$5.00—
🥈GPT-5.6 Sol (max)OpenAIOpenAI
77.4
AA Coding Index1.1M tokens$5.00—
🥉GPT-5.6 Sol (high)OpenAIOpenAI
77.2
AA Coding Index—$5.00—
4GPT-5.6 Terra (max)OpenAIOpenAI
76.7
AA Coding Index1.1M tokens$2.50—
5Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)AnthropicAnthropic
76.5
AA Coding Index1.0M tokens$10.00—
6GPT-5.6 Sol (medium)OpenAIOpenAI
76.3
AA Coding Index—$5.00—
7Kimi K3Kimi
76.2
AA Coding Index—$3.00—
8GPT-5.5OpenAIOpenAI
74.9
AA Coding Index1.1M tokens$5.00—
9Claude Opus 4.8 (Adaptive Reasoning, Max Effort)AnthropicAnthropic
74.3
AA Coding Index1.0M tokens$5.00—
10Claude Opus 4.7AnthropicAnthropic
73.6
AA Coding Index1.0M tokens$5.00—
11Claude Opus 4.7 (Fast)AnthropicAnthropic
73.6
AA Coding Index1.0M tokens$30.00—
12Grok 4.5xaixai
72.4
AA Coding Index500K tokens$2.00—
13Claude Sonnet 5anthropicanthropic
71.5
AA Coding Index1.0M tokens$2.00—
14GPT-5.5 ProOpenAIOpenAI
71.5
AA Coding Index1.1M tokens——
15GPT-5.6 Luna (max)OpenAIOpenAI
71.4
AA Coding Index1.1M tokens$1.00—
16Muse Spark 1.1 (xhigh)MetaMeta
71.3
AA Coding Index—$1.25—
17GPT-5.4OpenAIOpenAI
71.1
AA Coding Index1.1M tokens$2.50—
18GPT-5.4 ProOpenAIOpenAI
71.1
AA Coding Index1.1M tokens$30.00—
19GPT-5.6 Terra (xhigh)OpenAIOpenAI
70.6
AA Coding Index—$2.50—
20Google: Gemini 3.5 FlashGoogleGoogle
70.1
AA Coding Index1.0M tokens$1.50—
21Gemini 3.5 Flash (minimal)GoogleGoogle
70.1
AA Coding Index—$1.50—
22GPT-5.6 Sol (low)OpenAIOpenAI
69.7
AA Coding Index—$5.00—
23Gemini 3.1 Pro PreviewGoogleGoogle
68.8
AA Coding Index1.0M tokens$2.00—
24GLM-5.2 (max)Z.aiZ.ai
68.8
AA Coding Index—$1.40—
25Gemini 3.1googlegoogle
68.8
AA Coding Index———
26GPT-5.6 Luna (xhigh)OpenAIOpenAI
68.6
AA Coding Index—$1.00—
27GPT-5.6 Terra (high)OpenAIOpenAI
67.1
AA Coding Index—$2.50—
28Qwen3.7 MaxAlibabaAlibaba
66.0
AA Coding Index—$2.50—
29GPT-5.6 Sol (Non-reasoning)OpenAIOpenAI
65.1
AA Coding Index—$5.00—
30GPT-5.6 Terra (medium)OpenAIOpenAI
64.7
AA Coding Index—$2.50—
31GPT-5.6 Luna (high)OpenAIOpenAI
63.3
AA Coding Index—$1.00—
32Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)AnthropicAnthropic
63.0
AA Coding Index—$3.00—
33MoonshotAI: Kimi K2.6MoonshotAIMoonshotAI
61.8
AA Coding Index262K tokens$0.95✅
34Kimi K2.7 CodeKimi
60.8
AA Coding Index—$0.95—
35Xiaomi: MiMo-V2.5-ProXiaomi
60.2
AA Coding Index1.0M tokens$0.43—
36Kwaipilot: KAT-Coder-Pro V2Kwaipilot
59.5
AA Coding Index256K tokens$0.30—
37DeepSeek V4 ProDeepSeekDeepSeek
59.4
AA Coding Index1.0M tokens$0.43✅
38Nex-N2-ProNex AGI
59.1
AA Coding Index262K tokens$0.50—
39KAT-Coder-Pro V1KwaiKAT
58.9
AA Coding Index———
40Hy3-preview (Reasoning)Tencent
58.8
AA Coding Index262K tokens$0.12—
41Hy3-preview (Reasoning)Tencent
58.8
AA Coding Index262K tokens$0.12—
42Muse SparkMetaMeta
58.6
AA Coding Index———
43MiniMax-M3MiniMax
58.6
AA Coding Index1.0M tokens$0.30—
44GPT-5.6 Terra (low)OpenAIOpenAI
58.1
AA Coding Index—$2.50—
45MiMo-V2.5Xiaomi
56.8
AA Coding Index—$0.14—
46DeepSeek V4 FlashDeepSeekDeepSeek
56.2
AA Coding Index1.0M tokens$0.14✅
47GPT-5.4 MiniOpenAIOpenAI
56.1
AA Coding Index400K tokens$0.75—
48GPT-5.4 NanoOpenAIOpenAI
56.1
AA Coding Index400K tokens$0.20—
49Qwen3.7 PlusAlibabaAlibaba
55.9
AA Coding Index—$0.40—
50GLM-5.1 (Reasoning)Z.aiZ.ai
55.8
AA Coding Index—$1.40—
51MiniMax: MiniMax M2.7MiniMax
52.6
AA Coding Index197K tokens$0.30✅
52JT-4.1 Flash 236B A21BChina Mobile
52.4
AA Coding Index———
53GPT-5.6 Terra (Non-reasoning)OpenAIOpenAI
52.3
AA Coding Index—$2.50—
54Claude 4.5 Sonnet (Reasoning)AnthropicAnthropic
52.1
AA Coding Index—$3.00—
55Claude 4.5 Sonnet (Non-reasoning)AnthropicAnthropic
52.1
AA Coding Index—$3.00—
56InklingThinking Machines
52.1
AA Coding Index—$1.87—
57Grok Build 0.1 0616xAIxAI
51.5
AA Coding Index—$1.00—
58GPT-5.6 Luna (medium)OpenAIOpenAI
50.7
AA Coding Index—$1.00—
59MiMo-V2-Flash (Reasoning)Xiaomi
49.8
AA Coding Index262K tokens$0.10—
60MiMo-V2-Flash (Feb 2026)Xiaomi
49.8
AA Coding Index———
61GPT-5.1OpenAIOpenAI
49.4
AA Coding Index400K tokens$1.25—
62GPT-5.1-CodexOpenAIOpenAI
49.4
AA Coding Index400K tokens$1.25—
63GPT-5.1 ChatOpenAIOpenAI
49.4
AA Coding Index128K tokens$1.25—
64Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIANVIDIA
49.3
AA Coding Index1.0M tokens$0.68—
65Mistral: Mistral Medium 3.5Mistral AIMistral AI
46.9
AA Coding Index262K tokens$1.50✅
66Kimi K2 ThinkingKimi
46.8
AA Coding Index262K tokens$0.60—
67MoonshotAI: Kimi K2.5MoonshotAIMoonshotAI
46.8
AA Coding Index262K tokens$0.60✅
68Gemini 2.5 Pro Preview (Mar' 25)GoogleGoogle
46.7
AA Coding Index———
69Gemini 2.5 Pro Preview (May' 25)GoogleGoogle
46.7
AA Coding Index—$1.25—
70GLM-4.6 (Reasoning)Z.aiZ.ai
45.8
AA Coding Index—$0.55—
71GLM-4.6 (Non-reasoning)Z.aiZ.ai
45.8
AA Coding Index—$0.57—
72GLM-4.7 (Reasoning)Z.aiZ.ai
45.3
AA Coding Index—$0.60—
73LongCat 2.0LongCat
45.3
AA Coding Index———
74DeepSeek V3.2 Exp (Reasoning)DeepSeekDeepSeek
44.2
AA Coding Index—$0.28—
75DeepSeek V3.2DeepSeekDeepSeek
44.2
AA Coding Index164K tokens$0.28✅
76GPT-5.6 Luna (low)OpenAIOpenAI
44.2
AA Coding Index—$1.00—
77Claude 4.5 Haiku (Reasoning)AnthropicAnthropic
43.9
AA Coding Index—$1.00—
78DeepSeek V3.1 TerminusDeepSeekDeepSeek
43.5
AA Coding Index131K tokens$1.64✅
79Gemma 4 31BGoogleGoogle
43.4
AA Coding Index262K tokens$0.14—
80Ring-2.6-1TInclusionAI
42.8
AA Coding Index—$0.30—
81Grok 4.3xAIxAI
42.2
AA Coding Index1.0M tokens$1.25—
82o1OpenAIOpenAI
39.7
AA Coding Index200K tokens$15.00—
83Step 3.7 FlashStepFun
39.6
AA Coding Index—$0.20—
84GPT-5.5 Instant (May 2026)OpenAIOpenAI
39.4
AA Coding Index—$5.00—
85GPT-5.5 Instant (June 2026)OpenAIOpenAI
39.4
AA Coding Index—$5.00—
86GPT-5.6 Luna (Non-reasoning)OpenAIOpenAI
39.3
AA Coding Index—$1.00—
87Gemma 4 26B A4B GoogleGoogle
39.3
AA Coding Index262K tokens$0.13—
88GPT-5OpenAIOpenAI
37.8
AA Coding Index400K tokens$1.25—
89GPT-5 (ChatGPT)OpenAIOpenAI
37.8
AA Coding Index—$1.25—
90NVIDIA Nemotron 3 Super 120B A12B (Reasoning)NVIDIANVIDIA
37.7
AA Coding Index1.0M tokens$0.25—
91Claude 4 Sonnet (Reasoning)AnthropicAnthropic
37.6
AA Coding Index—$3.00—
92North Mini CodeCohereCohere
36.5
AA Coding Index———
93Claude 3.7 Sonnet (thinking)AnthropicAnthropic
36.4
AA Coding Index200K tokens——
94Claude 3.7 SonnetAnthropicAnthropic
36.4
AA Coding Index200K tokens$3.00—
95Gemini 3.1 Flash Lite PreviewGoogleGoogle
34.7
AA Coding Index1.0M tokens$0.25—
96Gemini 3.1 Flash LiteGoogleGoogle
34.7
AA Coding Index1.0M tokens$0.25—
97Nova 2.0 Pro Preview (medium)AmazonAmazon
34.0
AA Coding Index—$1.25—
98o1-previewOpenAIOpenAI
34.0
AA Coding Index—$16.50—
99Gemini 2.5GoogleGoogle
33.3
AA Coding Index———
100Gemini 2.5 ProGoogleGoogle
33.3
AA Coding Index1.0M tokens$1.25—
101Devstral 2MistralMistral
31.3
AA Coding Index———
102gpt-oss-120bOpenAIOpenAI
30.4
AA Coding Index131K tokens$0.15—
103Claude 3.5 Sonnet (Oct '24)AnthropicAnthropic
30.2
AA Coding Index—$3.00—
104Devstral Small 2MistralMistral
29.3
AA Coding Index———
105Qwen3.5 9B (Reasoning)AlibabaAlibaba
28.7
AA Coding Index———
106Command A+CohereCohere
27.8
AA Coding Index———
107Mistral: Mistral Small 4Mistral AIMistral AI
26.6
AA Coding Index262K tokens$0.15✅
108Mistral Small 3.1MistralMistral
26.3
AA Coding Index—$0.10—
109Claude 3.5 Sonnet (June '24)AnthropicAnthropic
26.0
AA Coding Index—$3.00—
110Gemini 2.0 Pro Experimental (Feb '25)GoogleGoogle
25.5
AA Coding Index———
111Ling 2.6 FlashInclusion AI
25.3
AA Coding Index—$0.10—
112DeepSeek R1 (Jan '25)DeepSeekDeepSeek
24.6
AA Coding Index—$1.35—
113DeepSeek: R1DeepSeekDeepSeek
24.6
AA Coding Index164K tokens$0.70✅
114GPT-4o (March 2025, chatgpt-4o-latest)OpenAIOpenAI
24.2
AA Coding Index———
115OpenAI: GPT-4o (2024-05-13)OpenAIOpenAI
24.2
AA Coding Index128K tokens$5.00—
116GPT-4o (2024-08-06)OpenAIOpenAI
24.2
AA Coding Index128K tokens$2.50—
117OpenAI: GPT-4oOpenAIOpenAI
24.2
AA Coding Index128K tokens$2.50—
118Gemini 2.0 FlashGoogleGoogle
24.1
AA Coding Index1.0M tokens$0.15—
119Gemini 2.0 Flash Thinking Experimental (Dec '24)GoogleGoogle
24.1
AA Coding Index———
120Gemini 2.0 Flash Thinking Experimental (Jan '25)GoogleGoogle
24.1
AA Coding Index———
121Gemini 2.0 Flash (experimental)GoogleGoogle
24.1
AA Coding Index———
122Gemini 1.5 Pro (Sep '24)GoogleGoogle
23.6
AA Coding Index———
123HyperNova 60B 2605Multiverse Computing
23.2
AA Coding Index—$0.04—
124Nova 2.0 Lite (high)AmazonAmazon
23.0
AA Coding Index—$0.30—
125DeepSeek V3DeepSeekDeepSeek
23.0
AA Coding Index131K tokens$0.36✅
126Qwen3.5 4B (Reasoning)AlibabaAlibaba
22.6
AA Coding Index—$0.03—
127Qwen: Qwen3 235B A22B Instruct 2507AlibabaAlibaba
22.1
AA Coding Index262K tokens$0.70✅
128Qwen: Qwen3 235B A22B Thinking 2507AlibabaAlibaba
22.1
AA Coding Index131K tokens$0.15✅
129GPT-4 TurboOpenAIOpenAI
21.5
AA Coding Index128K tokens$10.00—
130Magistral Medium 1.2Mistral AIMistral AI
21.3
AA Coding Index—$2.00—
131DeepSeek V3 0324DeepSeekDeepSeek
21.2
AA Coding Index—$1.14—
132K2 Think V2MBZUAI Institute of Foundation Models
21.0
AA Coding Index———
133gpt-oss-20bOpenAIOpenAI
20.7
AA Coding Index131K tokens$0.05—
134Mistral: Mistral Medium 3.1Mistral AIMistral AI
20.5
AA Coding Index131K tokens$0.40✅
135Qwen3.5 4B (Non-reasoning)AlibabaAlibaba
20.3
AA Coding Index—$0.03—
136GPT-4.1 MiniOpenAIOpenAI
20.2
AA Coding Index1.0M tokens$0.40—
137Mistral Large 3MistralMistral
20.1
AA Coding Index—$4.00—
138Gemini 1.5 Pro (May '24)GoogleGoogle
19.8
AA Coding Index———
139DiffusionGemma 26B A4BGoogleGoogle
19.7
AA Coding Index———
140Claude 3 OpusAnthropicAnthropic
19.5
AA Coding Index—$15.00—
141Gemini 1.0 UltraGoogleGoogle
17.6
AA Coding Index———
142Qwen3 Next 80B A3B (Reasoning)AlibabaAlibaba
17.4
AA Coding Index—$0.50—
143o3 Mini HighOpenAIOpenAI
16.3
AA Coding Index200K tokens$1.10—
144Llama 4 MaverickMetaMeta
16.3
AA Coding Index1.0M tokens$0.35✅
145Solar Pro 3Upstage
16.2
AA Coding Index128K tokens——
146Claude 3.5 HaikuAnthropicAnthropic
15.9
AA Coding Index200K tokens$0.80—
147GPT-5 MiniOpenAIOpenAI
15.6
AA Coding Index400K tokens$0.25—
148GPT-5 mini (minimal)OpenAIOpenAI
15.6
AA Coding Index—$0.25—
149Qwen3 32B (Reasoning)AlibabaAlibaba
15.3
AA Coding Index—$0.70—
150Magistral Small 1.2MistralMistral
14.7
AA Coding Index—$0.50—
151NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIANVIDIA
14.4
AA Coding Index—$0.05—
152Ministral 3 14BMistralMistral
14.4
AA Coding Index—$0.20—
153Claude 2.1AnthropicAnthropic
14.0
AA Coding Index———
154Qwen3 14B (Reasoning)AlibabaAlibaba
13.8
AA Coding Index—$0.35—
155OpenAI: GPT-4OpenAIOpenAI
13.1
AA Coding Index8K tokens$30.00—
156Claude 2.0AnthropicAnthropic
12.9
AA Coding Index———
157Mistral Small 3.2MistralMistral
12.5
AA Coding Index—$0.10—
158Qwen3 30B A3B 2507 (Reasoning)AlibabaAlibaba
12.1
AA Coding Index—$0.20—
159Llama 3.3 70B InstructMetaMeta
11.9
AA Coding Index131K tokens$0.58✅
160OpenAI: GPT-4o-miniOpenAIOpenAI
11.4
AA Coding Index128K tokens$0.15—
161GPT-4.1 NanoOpenAIOpenAI
11.1
AA Coding Index1.0M tokens$0.10—
162GPT-3.5 TurboOpenAIOpenAI
10.7
AA Coding Index—$0.50—
163Granite 4.1 30BIBM
10.4
AA Coding Index———
164Gemma 3 27BGoogleGoogle
10.1
AA Coding Index131K tokens——
165Ministral 3 8BMistralMistral
9.7
AA Coding Index—$0.15—
166Nanbeige4.1-3BNanbeige
9.6
AA Coding Index———
167Granite 4.1 8BIBM
9.5
AA Coding Index—$0.05—
168Qwen3 8B (Reasoning)AlibabaAlibaba
9.0
AA Coding Index—$0.18—
169Llama 4 ScoutMetaMeta
8.2
AA Coding Index10.0M tokens$0.17✅
170NVIDIA Nemotron 3 Nano 4BNVIDIANVIDIA
8.0
AA Coding Index———
171Claude InstantAnthropicAnthropic
7.8
AA Coding Index———
172Gemma 3 12BGoogleGoogle
5.8
AA Coding Index131K tokens——
173Llama 3.1 8B InstructMetaMeta
5.4
AA Coding Index16K tokens$0.10✅
174Ministral 3 3BMistralMistral
4.8
AA Coding Index—$0.10—
175Granite 4.1 3BIBM
4.7
AA Coding Index———
176PALM-2GoogleGoogle
4.6
AA Coding Index———
177Phi-4 Mini InstructMicrosoftMicrosoft
3.8
AA Coding Index———
178Gemma 3n E4B InstructGoogleGoogle
3.2
AA Coding Index—$0.02—
179Qwen3.5 2B (Reasoning)AlibabaAlibaba
2.9
AA Coding Index———
180Gemma 3 4BGoogleGoogle
2.7
AA Coding Index131K tokens——
181Qwen3.5 0.8B (Non-reasoning)AlibabaAlibaba
1.2
AA Coding Index———
182MiniCPM-V 4.6 1.3BOpenBMB
0.7
AA Coding Index———
183Qwen3.5 0.8B (Reasoning)AlibabaAlibaba
0.0
AA Coding Index———
184Gemini 3 Pro Preview (high)GoogleGoogle
92.0
LiveCodeBench—$2.00—
185Gemini 3 Flash Preview (Reasoning)GoogleGoogle
91.0
LiveCodeBench—$0.50—
186DeepSeek V3.2 SpecialeDeepSeekDeepSeek
90.0
LiveCodeBench164K tokens—✅
187GPT-5.2OpenAIOpenAI
89.0
LiveCodeBench400K tokens$1.75—
188Claude Opus 4.5 (Reasoning)AnthropicAnthropic
87.0
LiveCodeBench—$5.00—
189Gemini 3 Pro Preview (low)GoogleGoogle
86.0
LiveCodeBench—$2.00—
190o4 MiniOpenAIOpenAI
86.0
LiveCodeBench200K tokens$1.10—
191o4 Mini HighOpenAIOpenAI
85.9
LiveCodeBench200K tokens$1.10—
192GPT-5.1-Codex-MaxOpenAIOpenAI
84.9
LiveCodeBench400K tokens$1.25—
193GPT-5.1-Codex-MiniOpenAIOpenAI
84.0
LiveCodeBench400K tokens$0.25—
194GPT-5 CodexOpenAIOpenAI
84.0
LiveCodeBench400K tokens$1.25—
195Grok 4 FastxAIxAI
83.0
LiveCodeBench2.0M tokens$0.20—
196MiniMax-M2MiniMax
83.0
LiveCodeBench205K tokens$0.30—
197Grok 4xAIxAI
82.0
LiveCodeBench256K tokens$5.50—
198Grok 4.1 FastxAIxAI
82.0
LiveCodeBench2.0M tokens——
199MiniMax: MiniMax M2.1MiniMax
81.0
LiveCodeBench197K tokens$0.30✅
200o3OpenAIOpenAI
81.0
LiveCodeBench200K tokens$2.00—
201ERNIE 5.0 Thinking PreviewBaidu
81.0
LiveCodeBench———
202Apriel-v1.6-15B-ThinkerServiceNow
81.0
LiveCodeBench———
203o3 ProOpenAIOpenAI
80.8
LiveCodeBench200K tokens$20.00—
204Gemini 3 Flash Preview (Non-reasoning)GoogleGoogle
80.0
LiveCodeBench—$0.50—
205GPT-5 NanoOpenAIOpenAI
79.0
LiveCodeBench400K tokens$0.05—
206INTELLECT-3Prime Intellect
78.0
LiveCodeBench131K tokens—✅
207DeepSeek V3.1DeepSeekDeepSeek
78.0
LiveCodeBench164K tokens$0.59✅
208Doubao Seed CodeByteDance Seed
77.0
LiveCodeBench———
209Seed-OSS-36B-InstructByteDance Seed
77.0
LiveCodeBench—$0.21—
210K-EXAONE (Reasoning)LG AI
77.0
LiveCodeBench———
211GPT-5.2 ProOpenAIOpenAI
76.5
LiveBench Coding400K tokens$21.00—
212Claude Sonnet 4.5AnthropicAnthropic
76.1
LiveBench Coding1.0M tokens$3.00—
213EXAONE 4.0 32B (Reasoning)LG AI Research
75.0
LiveCodeBench———
214Gemini 3.5GoogleGoogle
74.6
LiveBench Coding———
215Claude Opus 4.5AnthropicAnthropic
74.0
LiveCodeBench200K tokens$5.00—
216GLM-4.5 (Reasoning)Z.aiZ.ai
74.0
LiveCodeBench131K tokens——
217Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIANVIDIA
74.0
LiveCodeBench—$0.40—
218Qwen3 VL 32B (Reasoning)AlibabaAlibaba
74.0
LiveCodeBench—$0.70—
219Apriel-v1.5-15B-ThinkerServiceNow
73.0
LiveCodeBench———
220o3 MiniOpenAIOpenAI
72.0
LiveCodeBench200K tokens$1.10—
221Falcon-H1R-7BTII UAE
72.0
LiveCodeBench———
222NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIANVIDIA
72.0
LiveCodeBench—$0.04—
223Gemini 2.5 Flash Preview (Sep '25) (Reasoning)GoogleGoogle
71.0
LiveCodeBench———
224MiniMax M1 80kMiniMax
71.0
LiveCodeBench—$0.55—
225Grok 3 MinixAIxAI
70.0
LiveCodeBench131K tokens$0.30—
226Gemini 2.5 Flash Preview (Reasoning)GoogleGoogle
70.0
LiveCodeBench—$0.30—
227Olmo 3.1 32B ThinkAllen Institute for AI
70.0
LiveCodeBench———
228Qwen3 VL 30B A3B (Reasoning)AlibabaAlibaba
70.0
LiveCodeBench—$0.20—
229NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIANVIDIA
70.0
LiveCodeBench131K tokens$0.05—
230Cogito v2.1 (Reasoning)Deep Cogito
69.0
LiveCodeBench—$1.25—
231K2-V2 (high)MBZUAI Institute of Foundation Models
69.0
LiveCodeBench———
232Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)GoogleGoogle
69.0
LiveCodeBench—$0.10—
233NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIANVIDIA
69.0
LiveCodeBench—$0.20—
234Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research
69.0
LiveCodeBench—$1.00—
235Ling-1TInclusionAI
68.0
LiveCodeBench———
236Qwen3 Omni 30B A3B (Reasoning)AlibabaAlibaba
68.0
LiveCodeBench—$0.25—
237Qwen: Qwen3 Next 80B A3B InstructAlibabaAlibaba
68.0
LiveCodeBench262K tokens$0.50✅
238GLM-4.5-AirZ.aiZ.ai
68.0
LiveCodeBench—$0.17—
239Olmo 3 32B ThinkAllenAI
67.0
LiveCodeBench66K tokens—✅
240MiniMax M1 40kMiniMax
66.0
LiveCodeBench———
241Nova 2.0 Omni (medium)AmazonAmazon
66.0
LiveCodeBench—$0.30—
242Grok Code Fast 1xAIxAI
66.0
LiveCodeBench256K tokens——
243Mi:dm K 2.5 ProKorea Telecom
66.0
LiveCodeBench———
244Claude 4.1 Opus (Non-reasoning)AnthropicAnthropic
65.4
LiveCodeBench—$15.00—
245xAI: Grok Build 0.1xAIxAI
65.4
LiveBench Coding256K tokens$1.00—
246Claude 4.1 Opus (Reasoning)AnthropicAnthropic
65.0
LiveCodeBench—$15.00—
247Qwen3 VL 235B A22B (Reasoning)AlibabaAlibaba
65.0
LiveCodeBench—$0.70—
248Qwen3 Max (Preview)AlibabaAlibaba
65.0
LiveCodeBench—$1.20—
249Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research
65.0
LiveCodeBench—$0.13—
250Motif-2-12.7B-ReasoningMotif Technologies
65.0
LiveCodeBench———
251Claude 4 Opus (Reasoning)AnthropicAnthropic
64.0
LiveCodeBench—$15.00—
252Ring-1TInclusionAI
64.0
LiveCodeBench———
253Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIANVIDIA
64.0
LiveCodeBench—$0.60—
254Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)GoogleGoogle
64.0
LiveCodeBench—$0.10—
255Qwen3 4B 2507 (Reasoning)AlibabaAlibaba
64.0
LiveCodeBench———
256QwQ 32BAlibabaAlibaba
63.0
LiveCodeBench—$0.66—
257HyperCLOVA X SEED Think (32B)Naver
63.0
LiveCodeBench———
258Ring-flash-2.0InclusionAI
63.0
LiveCodeBench—$0.14—
259Qwen3 235B A22B (Reasoning)AlibabaAlibaba
62.0
LiveCodeBench—$0.70—
260Solar Pro 2 (Non-reasoning)Upstage
62.0
LiveCodeBench———
261Olmo 3 7B ThinkAllen Institute for AI
62.0
LiveCodeBench———
262MoonshotAI: Kimi K2 0905MoonshotAIMoonshotAI
61.0
LiveCodeBench262K tokens$0.60✅
263GLM-4.5V (Reasoning)Z.aiZ.ai
60.0
LiveCodeBench—$0.60—
264Qwen: Qwen3 VL 235B A22B InstructAlibabaAlibaba
59.0
LiveCodeBench262K tokens$0.70✅
265Qwen3 Coder 480B A35B InstructAlibabaAlibaba
59.0
LiveCodeBench—$1.50—
266Nova 2.0 Omni (low)AmazonAmazon
59.0
LiveCodeBench—$0.30—
267Ling-flash-2.0InclusionAI
59.0
LiveCodeBench—$0.14—
268Gemini 2.5 Flash LiteGoogleGoogle
59.0
LiveCodeBench1.0M tokens$0.10—
269o1-miniOpenAIOpenAI
58.0
LiveCodeBench———
270Mi:dm K 2.5 Pro PreviewKorea Telecom
58.0
LiveCodeBench———
271GPT-5 (minimal)OpenAIOpenAI
56.0
LiveCodeBench—$1.25—
272Kimi K2Moonshot AIMoonshot AI
56.0
LiveCodeBench131K tokens$0.58—
273DeepSeek V3.2 Exp (Non-reasoning)DeepSeekDeepSeek
55.0
LiveCodeBench—$0.28—
274Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research
55.0
LiveCodeBench—$1.00—
275GPT-5.2-CodexOpenAIOpenAI
55.0
SciCode400K tokens$1.75—
276Claude Opus 4AnthropicAnthropic
54.0
LiveCodeBench200K tokens$15.00—
277Qwen3 Max Thinking (Preview)AlibabaAlibaba
54.0
LiveCodeBench—$1.20—
278K2-V2 (medium)MBZUAI Institute of Foundation Models
54.0
LiveCodeBench———
279Magistral Medium 1MistralMistral
53.0
LiveCodeBench———
280GPT-5.3-CodexOpenAIOpenAI
53.0
SciCode400K tokens$1.75—
281Qwen3 30B A3B 2507 InstructAlibabaAlibaba
52.0
LiveCodeBench—$0.20—
282Exaone 4.0 1.2B (Non-reasoning)LG AI Research
52.0
LiveCodeBench———
283Claude Opus 4.6 (Adaptive Reasoning, Max Effort)AnthropicAnthropic
52.0
SciCode—$5.00—
284Claude Haiku 4.5AnthropicAnthropic
51.0
LiveCodeBench200K tokens$1.00—
285Qwen: Qwen3 VL 32B InstructAlibabaAlibaba
51.0
LiveCodeBench131K tokens$0.70✅
286Qwen3 30B A3B (Reasoning)AlibabaAlibaba
51.0
LiveCodeBench—$0.20—
287Magistral Small 1MistralMistral
51.0
LiveCodeBench———
288DeepSeek R1 0528 Qwen3 8BDeepSeekDeepSeek
51.0
LiveCodeBench———
289Qwen: Qwen3 30B A3B Thinking 2507AlibabaAlibaba
50.6
LiveCodeBench131K tokens$0.08✅
290Gemini 2.5 FlashGoogleGoogle
50.0
LiveCodeBench1.0M tokens$0.30—
291Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)NVIDIANVIDIA
49.0
LiveCodeBench———
292Qwen: Qwen3 VL 30B A3B InstructAlibabaAlibaba
48.0
LiveCodeBench131K tokens$0.20✅
293Baidu: ERNIE 4.5 300B A47B Baidu
47.0
LiveCodeBench123K tokens$0.28✅
294GPT-5 nano (minimal)OpenAIOpenAI
47.0
LiveCodeBench—$0.05—
295EXAONE 4.0 32B (Non-reasoning)LG AI Research
47.0
LiveCodeBench———
296Qwen3 4B (Reasoning)AlibabaAlibaba
47.0
LiveCodeBench———
297Qwen3.6 Max PreviewAlibabaAlibaba
47.0
SciCode—$1.30—
298Claude Sonnet 4.6AnthropicAnthropic
47.0
SciCode1.0M tokens$3.00—
299GPT-4.1OpenAIOpenAI
46.0
LiveCodeBench1.0M tokens$2.00—
300Solar Pro 2 (Preview) (Reasoning)Upstage
46.0
LiveCodeBench———
301Grok 4.20xAIxAI
46.0
SciCode2.0M tokens$2.00—
302GLM-5 (Reasoning)Z.aiZ.ai
46.0
SciCode203K tokens$1.00—
303Claude Opus 4.6AnthropicAnthropic
46.0
SciCode1.0M tokens$5.00—
304Claude Sonnet 4AnthropicAnthropic
45.0
LiveCodeBench1.0M tokens$3.00—
305Grok 4.20 0309 (Reasoning)xAIxAI
45.0
SciCode—$2.00—
306Reka Flash 3Reka Flash 3
44.0
LiveCodeBench66K tokens$0.20✅
307GLM 5V Turbo (Reasoning)Z.aiZ.ai
44.0
SciCode203K tokens——
308GLM-5-TurboZ.aiZ.ai
44.0
SciCode203K tokens——
309Claude Sonnet 4.6 (Non-reasoning, Low Effort)AnthropicAnthropic
44.0
SciCode—$3.00—
310Grok 3xAIxAI
43.0
LiveCodeBench131K tokens$4.00—
311Ling-mini-2.0InclusionAI
43.0
LiveCodeBench———
312Xiaomi: MiMo-V2-ProXiaomi
43.0
SciCode1.0M tokens——
313MiniMax: MiniMax M2.5MiniMax
43.0
SciCode197K tokens$0.30✅
314Qwen3 Omni 30B A3B InstructAlibabaAlibaba
42.0
LiveCodeBench—$0.25—
315GLM-4.6V (Non-reasoning)Z.aiZ.ai
41.0
LiveCodeBench—$0.30—
316Gemini 2.5 Flash Preview (Non-reasoning)GoogleGoogle
41.0
LiveCodeBench———
317Qwen3.5 Omni PlusAlibabaAlibaba
41.0
SciCode—$0.40—
318Mistral: Mistral Medium 3Mistral AIMistral AI
40.0
LiveCodeBench131K tokens$0.40✅
319Qwen: Qwen3 Coder 30B A3B InstructAlibabaAlibaba
40.0
LiveCodeBench160K tokens$0.45✅
320MiMo-V2-Omni-0327Xiaomi
40.0
SciCode———
321Step 3.5 FlashStepFun
40.0
SciCode—$0.10—
322Solar Pro 2 (Preview) (Non-reasoning)Upstage
39.0
LiveCodeBench———
323Step 3.5 FlashStepFun
39.0
SciCode262K tokens$0.10✅
324Inception: Mercury 2Inception
39.0
SciCode128K tokens$0.25—
325DeepSeek R1 Distill Qwen 14BDeepSeekDeepSeek
38.0
LiveCodeBench———
326Kimi Linear 48B A3B InstructKimi
38.0
LiveCodeBench———
327Qwen3 4B 2507 InstructAlibabaAlibaba
38.0
LiveCodeBench———
328Gemma 4 12B (Reasoning)GoogleGoogle
38.0
SciCode—$0.10—
329GLM-5 (Non-reasoning)Z.aiZ.ai
38.0
SciCode—$1.00—
330Ling-2.6-1TInclusion AI
37.0
SciCode—$0.30—
331Xiaomi: MiMo-V2-OmniXiaomi
37.0
SciCode262K tokens——
332Qwen2.5 MaxAlibabaAlibaba
36.0
LiveCodeBench———
333NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIANVIDIA
36.0
LiveCodeBench262K tokens$0.05—
334GLM-5.1 (Non-reasoning)Z.aiZ.ai
36.0
SciCode—$1.40—
335Trinity Large ThinkingArcee AI
36.0
SciCode—$0.23—
336Qwen3 VL 8B (Reasoning)AlibabaAlibaba
35.0
LiveCodeBench—$0.18—
337GLM-4.5V (Non-reasoning)Z.aiZ.ai
35.0
LiveCodeBench—$0.60—
338NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIANVIDIA
35.0
LiveCodeBench—$0.20—
339Nemotron Cascade 2 30B A3BNVIDIANVIDIA
35.0
SciCode———
340Mistral: Devstral MediumMistral AIMistral AI
34.0
LiveCodeBench131K tokens$0.40✅
341QwQ 32B-PreviewAlibabaAlibaba
34.0
LiveCodeBench———
342GLM-4.7-Flash (Reasoning)Z.aiZ.ai
34.0
SciCode—$0.07—
343Qwen: Qwen3 VL 8B InstructAlibabaAlibaba
33.0
LiveCodeBench131K tokens$0.18✅
344GPT-4o (ChatGPT)OpenAIOpenAI
33.0
SciCode———
345Amazon: Nova Premier 1.0AmazonAmazon
32.0
LiveCodeBench1.0M tokens$2.50—
346Qwen: Qwen3 30B A3B Instruct 2507AlibabaAlibaba
32.0
LiveCodeBench262K tokens$0.20✅
347Qwen3 VL 4B (Reasoning)AlibabaAlibaba
32.0
LiveCodeBench———
348Llama 3.1 Instruct 405BMetaMeta
31.0
LiveCodeBench—$2.75—
349Nova 2.0 Omni (Non-reasoning)AmazonAmazon
31.0
LiveCodeBench—$0.30—
350Qwen3 1.7B (Reasoning)AlibabaAlibaba
31.0
LiveCodeBench———
351Step3 VL 10BStepFun
31.0
SciCode———
352Qwen2.5 Coder 32B InstructAlibabaAlibaba
30.0
LiveCodeBench33K tokens—✅
353SonarPerplexityPerplexity
30.0
LiveCodeBench127K tokens——
354Sarvam M (Reasoning)Sarvam
30.0
LiveCodeBench———
355Llama 3.1 Tulu3 405BAllen Institute for AI
29.0
LiveCodeBench———
356Mistral Large 2 (Nov '24)MistralMistral
29.0
LiveCodeBench—$2.00—
357Qwen3 32B (Non-reasoning)AlibabaAlibaba
29.0
LiveCodeBench—$0.70—
358Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIANVIDIA
29.0
LiveCodeBench—$0.40—
359Qwen3 VL 4B InstructAlibabaAlibaba
29.0
LiveCodeBench———
360JT-35B-FlashChina Mobile
29.0
SciCode———
361Llama 3.3 Nemotron Super 49B v1 (Reasoning)NVIDIANVIDIA
28.0
LiveCodeBench———
362Qwen3 14B (Non-reasoning)AlibabaAlibaba
28.0
LiveCodeBench—$0.35—
363Qwen2.5 72B InstructAlibabaAlibaba
28.0
LiveCodeBench33K tokens$0.47✅
364Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)NVIDIANVIDIA
28.0
LiveCodeBench———
365Sonar Reasoning ProPerplexityPerplexity
28.0
LiveCodeBench128K tokens——
366Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIANVIDIA
28.0
SciCode—$0.07—
367EXAONE 4.5 33BLG AI
28.0
SciCode———
368LongCat Flash LiteLongCat
28.0
SciCode———
369DeepSeek: R1 Distill Qwen 32BDeepSeekDeepSeek
27.0
LiveCodeBench128K tokens—✅
370R1 Distill Llama 70BDeepSeekDeepSeek
27.0
LiveCodeBench128K tokens$0.70✅
371Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research
27.0
LiveCodeBench—$0.13—
372Grok 2 (Dec '24)xAIxAI
27.0
LiveCodeBench———
373Gemini 1.5 Flash (Sep '24)GoogleGoogle
27.0
LiveCodeBench———
374Mistral Large 2 (Jul '24)MistralMistral
27.0
LiveCodeBench131K tokens$2.00—
375Olmo 3 7B InstructAllen Institute for AI
27.0
LiveCodeBench—$0.10—
376JT-MINIChina Mobile
27.0
SciCode———
377Solar Open 100B (Reasoning)Upstage
27.0
SciCode———
378Mistral: Pixtral Large 2411Mistral AIMistral AI
26.0
LiveCodeBench131K tokens$2.00—
379Devstral Small (May '25)MistralMistral
26.0
LiveCodeBench———
380Qwen3.5 Omni FlashAlibabaAlibaba
26.0
SciCode—$0.10—
381Sarvam 105B (high)Sarvam
26.0
SciCode—$0.04—
382Devstral Small (Jul '25)MistralMistral
25.0
LiveCodeBench131K tokens$0.10—
383Mistral Small 3MistralMistral
25.0
LiveCodeBench—$0.10—
384Qwen2.5 Instruct 32BAlibabaAlibaba
25.0
LiveCodeBench———
385Granite 4.0 H SmallIBM
25.0
LiveCodeBench—$0.06—
386Grok BetaxAIxAI
24.0
LiveCodeBench———
387Gemma 4 E4B (Reasoning)GoogleGoogle
24.0
SciCode———
388Mistral: SabaMistral AIMistral AI
24.0
SciCode33K tokens—✅
389Llama 3.1 70B InstructMetaMeta
23.0
LiveCodeBench131K tokens$0.56✅
390Microsoft: Phi 4MicrosoftMicrosoft
23.0
LiveCodeBench16K tokens$0.13✅
391Nova ProAmazonAmazon
23.0
LiveCodeBench—$0.80—
392Qwen3 4B (Non-reasoning)AlibabaAlibaba
23.0
LiveCodeBench———
393DeepSeek R1 Distill Llama 8BDeepSeekDeepSeek
23.0
LiveCodeBench———
394Gemini 1.5 Flash-8BGoogleGoogle
22.0
LiveCodeBench———
395Llama 3.2 Instruct 90B (Vision)MetaMeta
21.0
LiveCodeBench—$1.38—
396Jamba Reasoning 3BAI21 Labs
21.0
LiveCodeBench———
397Gemma 4 E2B (Reasoning)GoogleGoogle
21.0
SciCode———
398DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Nous Research
20.0
LiveCodeBench———
399Llama 3 70B InstructMetaMeta
20.0
LiveCodeBench8K tokens$0.65✅
400Gemini 1.5 Flash (May '24)GoogleGoogle
20.0
LiveCodeBench———
401Qwen3 8B (Non-reasoning)AlibabaAlibaba
20.0
LiveCodeBench—$0.18—
402Gemma 4 E2B (Non-reasoning)GoogleGoogle
20.0
SciCode———
403Gemini 2.0 Flash-Lite (Feb '25)GoogleGoogle
19.0
LiveCodeBench———
404Hermes 3 - Llama-3.1 70BNous Research
19.0
LiveCodeBench—$0.70—
405Sarvam 30BSarvam
19.0
SciCode—$0.03—
406Gemini 2.0 Flash-Lite (Preview)GoogleGoogle
18.0
LiveCodeBench———
407Claude 3 SonnetAnthropicAnthropic
18.0
LiveCodeBench—$3.00—
408AI21: Jamba Large 1.7AI21 Labs
18.0
LiveCodeBench256K tokens$2.00✅
409Granite 4.0 MicroIBM
18.0
LiveCodeBench131K tokens—✅
410Tri-21B-think PreviewTrillion Labs
18.0
SciCode———
411Mistral LargeMistral AIMistral AI
17.8
LiveCodeBench128K tokens$2.00✅
412Llama 3.1 Nemotron 70B InstructNVIDIANVIDIA
17.0
LiveCodeBench131K tokens$1.20✅
413Jamba 1.6 LargeAI21 Labs
17.0
LiveCodeBench—$2.00—
414Nova LiteAmazonAmazon
17.0
LiveCodeBench—$0.06—
415Tri-21B-ThinkTrillion Labs
17.0
SciCode———
416Olmo 3.1 32B InstructAllenAI
17.0
SciCode66K tokens—✅
417GLM-4.6V (Reasoning)Z.aiZ.ai
16.0
LiveCodeBench—$0.30—
418Qwen2 Instruct 72BAlibabaAlibaba
16.0
LiveCodeBench———
419DeepSeek Coder V2 Lite InstructDeepSeekDeepSeek
16.0
LiveCodeBench———
420Mixtral 8x22B InstructMistralMistral
15.0
LiveCodeBench———
421Anthropic: Claude 3 HaikuAnthropicAnthropic
15.0
LiveCodeBench200K tokens$0.25—
422LFM2 8B A1BLiquid AI
15.0
LiveCodeBench———
423Mistral: Mixtral 8x22B InstructMistral AIMistral AI
14.8
LiveCodeBench66K tokens$2.00✅
424Mistral Small (Sep '24)MistralMistral
14.0
LiveCodeBench—$0.20—
425Jamba 1.5 LargeAI21 Labs
14.0
LiveCodeBench—$2.00—
426Gemma 3n E4B Instruct Preview (May '25)GoogleGoogle
14.0
LiveCodeBench———
427Nova MicroAmazonAmazon
14.0
LiveCodeBench—$0.04—
428Qwen2.5 Coder Instruct 7B AlibabaAlibaba
13.0
LiveCodeBench———
429Phi-4 Multimodal InstructMicrosoftMicrosoft
13.0
LiveCodeBench———
430Granite 3.3 8B (Non-reasoning)IBM
13.0
LiveCodeBench—$0.03—
431Qwen3 1.7B (Non-reasoning)AlibabaAlibaba
13.0
LiveCodeBench———
432Molmo2-8BAllen Institute for AI
13.0
SciCode———
433Cohere: Command R+ (08-2024)CohereCohere
12.2
LiveCodeBench128K tokens$2.50—
434Command-R+ (Apr '24)CohereCohere
12.0
LiveCodeBench—$3.00—
435Gemini 1.0 ProGoogleGoogle
12.0
LiveCodeBench———
436Phi-3 Mini Instruct 3.8BMicrosoftMicrosoft
12.0
LiveCodeBench———
437Granite 4.0 H 1BIBM
12.0
LiveCodeBench———
438Qwen3 0.6B (Reasoning)AlibabaAlibaba
12.0
LiveCodeBench———
439OpenChat 3.5 (1210)OpenChat
12.0
LiveCodeBench———
440Mistral Small (Feb '24)MistralMistral
11.0
LiveCodeBench—$1.00—
441Llama 3.2 11B Vision InstructMetaMeta
11.0
LiveCodeBench131K tokens$0.34✅
442LFM2-24B-A2BLiquidAI
11.0
SciCode33K tokens—✅
443Llama 3 8B InstructMetaMeta
10.0
LiveCodeBench8K tokens$0.04✅
444Mistral MediumMistralMistral
10.0
LiveCodeBench—$2.75—
445Llama 2 Chat 13BMetaMeta
10.0
LiveCodeBench———
446LFM 40BLiquid AI
10.0
LiveCodeBench———
447Gemma 3n E2B InstructGoogleGoogle
10.0
LiveCodeBench———
448Llama 2 Chat 70BMetaMeta
10.0
LiveCodeBench———
449DBRX InstructDatabricks
9.0
LiveCodeBench———
450DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Nous Research
9.0
LiveCodeBench———
451Llama 3.2 3B InstructMetaMeta
8.0
LiveCodeBench80K tokens$0.15✅
452LFM2 2.6BLiquid AI
8.0
LiveCodeBench———
453LFM2.5-8B-A1BLiquid AI
8.0
SciCode———
454Jamba 1.6 MiniAI21 Labs
7.0
LiveCodeBench—$0.20—
455OLMo 2 32BAllen Institute for AI
7.0
LiveCodeBench———
456DeepSeek R1 Distill Qwen 1.5BDeepSeekDeepSeek
7.0
LiveCodeBench———
457Qwen3 0.6B (Non-reasoning)AlibabaAlibaba
7.0
LiveCodeBench———
458Mistral: Mixtral 8x7B InstructMistral AIMistral AI
7.0
LiveCodeBench33K tokens$0.45✅
459Jamba 1.7 MiniAI21 Labs
6.0
LiveCodeBench———
460Jamba 1.5 MiniAI21 Labs
6.0
LiveCodeBench—$0.20—
461Apertus 70B InstructSwiss AI Initiative
6.0
SciCode—$0.82—
462Granite 4.0 1BIBM
5.0
LiveCodeBench———
463Command-R (Mar '24)CohereCohere
5.0
LiveCodeBench—$0.50—
464Mistral 7B InstructMistralMistral
5.0
LiveCodeBench—$0.25—
465OLMo 2 7BAllen Institute for AI
4.0
LiveCodeBench———
466Molmo 7B-DAllen Institute for AI
4.0
LiveCodeBench———
467MiniCPM5-1B (Non-reasoning)OpenBMB
4.0
SciCode———
468Gemma 4 E4B (Non-reasoning)GoogleGoogle
4.0
SciCode———
469Tiny Aya GlobalCohereCohere
4.0
SciCode———
470LFM2.5-1.2B-ThinkingLiquid AI
4.0
SciCode———
471Apertus 8B InstructSwiss AI Initiative
4.0
SciCode—$0.10—
472LFM2.5-VL-1.6BLiquid AI
3.0
SciCode———
473LFM2 1.2BLiquid AI
2.0
LiveCodeBench———
474Granite 4.0 H 350MIBM
2.0
LiveCodeBench———
475Llama 3.2 1B InstructMetaMeta
2.0
LiveCodeBench60K tokens$0.10✅
476Granite 4.0 350MIBM
2.0
LiveCodeBench———
477Gemma 3 1B InstructGoogleGoogle
2.0
LiveCodeBench———
478LFM2.5-1.2B-InstructLiquid AI
2.0
SciCode———
479Gemma 3 270MGoogleGoogle
0.0
LiveCodeBench———
480Llama 2 Chat 7BMetaMeta
0.0
LiveCodeBench—$0.05—

+ 180 models without coding benchmarks available.View all models

Complete Guide: AI for Programming in 2026

The State of AI for Code in 2026

Artificial intelligence has fundamentally changed software development. In 2026, large language models (LLMs) can generate working code in dozens of languages, fix bugs in production codebases, and build complete applications from plain-English descriptions. SWE-bench — the most rigorous coding benchmark — evaluates models on real software engineering tasks pulled from GitHub issues.

SWE-bench: The Gold Standard

SWE-bench (Software Engineering Benchmark) is widely considered the gold standard for evaluating LLM coding ability. Unlike academic benchmarks like HumanEval (which tests isolated functions), SWE-bench presents real issues from popular repositories such as Django, Flask, scikit-learn, and requests. The model must understand the project context, locate the relevant files, and generate a patch that resolves the bug — mirroring the actual workflow of a professional developer.

The “Verified” variant (SWE-bench Verified) is curated by human engineers to ensure every task has a clear, verifiable solution. Scores on this benchmark correlate strongly with real-world coding performance, making it the single most informative metric when choosing an AI coding assistant.

HumanEval and LiveCodeBench

HumanEval, created by OpenAI, tests a model's ability to generate Python functions from docstrings. It is simpler than SWE-bench but useful for gauging basic code fluency. LiveCodeBench raises the bar by using problems that are refreshed regularly, reducing the risk of data contamination — a concern when a model may have seen the answers during training.

How to Choose the Best AI Model for Code

The right model depends on your specific use case. For real-time code autocomplete (Cursor, Copilot), speed and latency matter more than peak benchmark scores — lighter mini and flash-class models often deliver the best speed-to-quality ratio. For full project generation or complex debugging, frontier models like Claude Fable 5, GPT-5.5 and Gemini 3.5-class systems are better suited, despite higher costs.

Teams with strict data control requirements (compliance, security) should consider open-source models like DeepSeek Coder, Code Llama, and StarCoder, which can be deployed on-premises with competitive performance. The trade-off between proprietary and open-source involves cost, latency, privacy, and quality considerations.

AI-Powered Coding Tools

The leading AI-assisted development tools in 2026 include Cursor, GitHub Copilot, Windsurf and agentic IDE workflows that let you swap between multiple frontier models. Each tool uses different models under the hood, and the quality of generated code depends directly on the LLM powering it.

Trends for 2026 and Beyond

The most significant trends in AI for code include autonomous software engineering agents (that solve complex tasks without supervision), automated test generation, intelligent refactoring, and native CI/CD pipeline integration. The frontier is shifting from “code assistant” to “autonomous engineer”, with models increasingly capable of navigating large codebases and making architectural decisions.

Frequently Asked Questions

What is the best AI for coding?

In 2026, the top models on coding benchmarks are GPT-5.6 Sol (xhigh), GPT-5.6 Sol (max), GPT-5.6 Sol (high). The best choice depends on your use case: code autocomplete, full project generation, debugging, or code review.

ChatGPT or Claude for code?

Today the strongest current options usually cluster around Claude Fable 5 / Opus 4.8, GPT-5.5 and Gemini 3.5-class models. Claude tends to shine in long-context refactors; GPT is strong in fast generation and tool use. Test with your own repository and workflow.

What is SWE-bench?

SWE-bench (Software Engineering Benchmark) evaluates how well models can resolve real issues from open-source GitHub repositories. It is considered the most realistic coding benchmark because it tests bug resolution in real projects, not academic exercises.

Which free LLMs are good for coding?

Open-source models like DeepSeek Coder, Qwen Coder, and Code Llama offer excellent coding performance with no API cost. You can run them locally with Ollama or access them for free on platforms like Together AI and Groq.

What coding benchmarks matter most?

SWE-bench Verified is the gold standard for real-world coding ability. HumanEval tests basic function generation, while LiveCodeBench uses regularly updated problems to reduce data contamination. For a complete picture, look at all three.

Explore Other Categories

All ModelsOpen SourceImageAudioVideoCompareMethodologyModelsDev ToolsDev Ranking