llmboard.aiLeaderboard Center
Overall
Overall RankingOpen Models
Tools
Model DirectoryCompare Models
Capabilities
CodingReasoningMathKnowledgeInstruction Following
Price & Efficiency
Price & ValueCapability vs. PriceRuntime Performance
Modalities
Image GenerationVideo GenerationSpeech ModelsEmbeddings
Core Benchmarks
GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-ProView all benchmarks
Methods
Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

Capability ranking

Best AI for Coding

Best AI Models for Coding

Updated 2026-08-11

Ranked models98
Vendors21
Open-weight models33
Official prices69

On this page

  • Overview
  • Leaders
  • Capability
  • Ranking
  • Value
  • Composition
  • Compare
  • FAQ

What this ranking says

A quick reading of the current coding ranking before the full data table.

Claude Mythos leads this page at 98.7, 4.6 points ahead of Claude Fable 5.

Kimi K3 is the highest-ranked open-weight option at #4. Step 3.5 Flash has the lowest official input price among ranked models.

Top coding modelClaude Mythos98.7 coding scoreBest open-weight modelKimi K3Rank #4Lowest official inputStep 3.5 Flash$0.10 / 1MLargest contextGPT-5.6-Sol1.1M tokens

Coding Ranking Leaders

The leading coding scores, with the axis focused on the competitive range rather than zero.

Top coding models

Coding Capability Profile

Compare coding strength with each model's broader capability score.

ModelReasoningKnowledgeMathCodingInstruction
Claude MythosAnthropic99.899.7100.098.7N/A
Claude Fable 5AnthropicN/A97.8N/A94.1N/A
GPT-5.6-SolOpenAI99.886.3100.093.6N/A
Kimi K3Moonshot AI97.491.3N/A90.5N/A
Claude Opus 4.8Anthropic99.094.6N/A85.7N/A
25.245.365.385.3105.3-7.720.147.975.7103.5Coding scoreOverall score
80 models with comparable dataOpen a model by selecting its logo
GPQA94.6%Claude Mythos Preview80 compared models
MMLU-Pro89.6%Qwen3.7 Max52 compared models
AIME 2025100.0%Kimi K2-Thinking-090535 compared models
SWE-Bench Verified95.0%Claude Fable 561 compared models
MMLU90.8%GPT-4.520 compared models
Humanity's Last Exam64.7%Claude Mythos Preview56 compared models
LiveCodeBench93.5%DeepSeek-V4-Pro-Max28 compared models
MATH97.9%o3-mini15 compared models

Coding Model Ranking

Models are ordered by their coding score.

98 rows
Columns

Show columns

01ANClaude MythosAnthropicClaude Mythos Preview98.793.699.899.7100.0N/A80.0%N/AClosed weightsN/AN/A
02ANClaude Fable 5AnthropicClaude Fable 594.195.8N/A97.8N/AN/A40.0%1MClosed weights$10$50
03OPGPT-5.6-SolOpenAIGPT-5.6 Sol93.695.199.886.3100.0N/A80.0%1.1MClosed weights$5$30
04MAKimi K3Moonshot AIKimi K390.593.097.491.3N/AN/A60.0%1MOpen weights$3$15
05ANClaude Opus 4.8AnthropicClaude Opus 4.885.787.999.094.6N/AN/A60.0%1MClosed weights$5$25
06ACQwen3.7 MaxAlibaba Cloud / Qwen TeamQwen3.7 Max85.678.891.589.193.192.2100.0%1MClosed weights$2.5$7.5
07ACQwen3.8 MaxAlibaba Cloud / Qwen TeamQwen3.8 Max80.189.397.670.7N/A100.080.0%1MClosed weights$2$6
08ANClaude Sonnet 5AnthropicClaude Sonnet 579.284.0N/A93.550.0N/A60.0%1MClosed weights$2$10
09OPGPT-5.6-TerraOpenAIGPT-5.6 Terra78.887.696.156.393.8N/A80.0%1.1MClosed weights$2$12
10ANClaude Opus 4.6AnthropicClaude Opus 4.674.779.683.287.795.6N/A80.0%1MClosed weights$5$25
11OPGPT-5.5OpenAIGPT-5.574.384.099.083.762.5N/A80.0%1.1MClosed weights$5$30
12ANClaude Opus 4.7AnthropicClaude Opus 4.771.584.298.790.1N/AN/A60.0%1MClosed weights$5$25
13MAKimi K2.6Moonshot AIKimi K2.671.275.592.358.772.7N/A80.0%262.1KOpen weights$0.95$4
14OPMiniCPM SALAOpenBMBMiniCPM-SALA69.622.336.426.636.312.5100.0%N/AClosed weightsN/AN/A
15ACQwen2.5 32BAlibaba Cloud / Qwen TeamQwen2.5 32B Instruct68.314.850.637.481.7N/A80.0%N/AClosed weights$0.70$2.8
16ACQwen2.5 Coder 32BAlibaba Cloud / Qwen TeamQwen2.5-Coder 32B Instruct68.04.446.317.239.3N/A80.0%128KClosed weights$0.287$0.861
17AMNova 2 ProAmazonNova 2 Pro67.852.566.768.068.694.7100.0%N/AClosed weightsN/AN/A
18OPGPT-5.6-LunaOpenAIGPT-5.6 Luna67.876.494.035.087.5N/A80.0%1.1MClosed weights$0.20$1.2
19DEDeepSeek-V4-FlashDeepSeekDeepSeek-V4-Flash-073166.978.3N/AN/AN/AN/A20.0%1MOpen weights$0.14$0.28
20GOGemini 2.5 ProGoogleGemini 2.5 Pro Preview 06-0566.149.981.178.754.9100.0100.0%1MClosed weights$1.25$10
21XAGrok 4.5xAIGrok 4.564.982.296.6N/AN/AN/A40.0%500KClosed weights$2$6
22DEDeepSeek-V4-ProDeepSeekDeepSeek-V4-Pro-Max63.773.890.184.883.9N/A80.0%1MClosed weights$0.435$0.87
23XIMiMo V2 ProXiaomiMiMo-V2-Pro62.664.0N/AN/AN/AN/A20.0%1MClosed weights$0.435$0.87
24ACQwen3.7 PlusAlibaba Cloud / Qwen TeamQwen3.7-Plus61.673.884.783.566.987.8100.0%1MClosed weights$0.50$3
25MAKimi K2 ThinkingMoonshot AIKimi K2-Thinking-090561.061.075.582.065.70.0100.0%262.1KClosed weights$0.60$2.5
26MIMiniMax M2.1MiniMaxMiniMax M2.160.953.765.269.239.839.3100.0%204.8KOpen weights$0.30$1.2
27ZAGLM 4.6Zhipu AIGLM-4.660.854.265.229.976.1N/A80.0%204.8KOpen weights$0.60$2.2
28STStep 3.5 FlashStepFunStep-3.5-Flash60.460.4N/AN/A72.0N/A40.0%256KOpen weights$0.10$0.30
29ACQwen2.5 72BAlibaba Cloud / Qwen TeamQwen2.5 72B Instruct60.321.422.537.580.168.4100.0%131.1KClosed weights$1.4$5.6
30SASarvam 30BSarvam AISarvam-30B59.834.339.157.859.1N/A80.0%128KOpen weightsN/AN/A
31OPo4 miniOpenAIo4-mini58.545.066.722.370.828.6100.0%200KClosed weights$1.1$4.4
32ACQwen3.5 397B A17BAlibaba Cloud / Qwen TeamQwen3.5-397B-A17B57.466.381.382.850.181.9100.0%262.1KOpen weights$0.60$3.6
33ZAGLM 5.2Zhipu AIGLM-5.256.079.392.788.689.8N/A80.0%1MOpen weights$1.4$4.4
34OPGPT-5.4OpenAIGPT-5.455.277.191.263.081.3N/A80.0%1.1MClosed weights$2.5$15
35BYSeed 2.1 ProByteDanceSeed 2.1 Pro54.378.795.590.633.3N/A80.0%N/AClosed weightsN/AN/A
36ACQwen3.5 122B A10BAlibaba Cloud / Qwen TeamQwen3.5-122B-A10B54.259.267.484.656.369.8100.0%262.1KOpen weights$0.40$3.2
37DEDeepSeek-V3.2DeepSeekDeepSeek-V3.2-Speciale54.158.1N/A54.488.5N/A60.0%131.1KClosed weights$0.14$0.28
38GOGemini 3.1 ProGoogleGemini 3.1 Pro54.077.596.290.3N/AN/A60.0%1MClosed weights$2$12
39ZAGLM 5.1Zhipu AIGLM-5.153.869.680.784.868.1N/A80.0%200KOpen weights$1.4$4.4
40TEHy3TencentHy353.571.091.40.086.1N/A80.0%256KOpen weightsN/AN/A
41MEMuse Spark 1.1MetaMuse Spark 1.152.188.3N/A96.7N/AN/A40.0%1MClosed weights$1.25$4.25
42ACQwen3.6 PlusAlibaba Cloud / Qwen TeamQwen3.6 Plus51.867.580.987.373.372.7100.0%1MClosed weights$0.50$3
43OPo3 miniOpenAIo3-mini51.736.358.146.963.870.0100.0%200KClosed weights$1.1$4.4
44ACQwen2.5 14BAlibaba Cloud / Qwen TeamQwen2.5 14B Instruct51.28.220.340.073.1N/A80.0%N/AClosed weights$0.35$1.4
45ACQwen3 235B A22BAlibaba Cloud / Qwen TeamQwen3-235B-A22B-Instruct-250751.242.461.170.621.572.8100.0%262.1KOpen weights$0.70$2.8
46ACQwen2.5 Coder 7BAlibaba Cloud / Qwen TeamQwen2.5-Coder 7B Instruct50.50.022.83.719.9N/A80.0%N/AClosed weights$0.144$0.287
47MIMiniMax M2MiniMaxMiniMax M249.843.959.443.934.5N/A80.0%196.6KOpen weights$0.30$1.2
48XIMiMo V2.5 ProXiaomiMiMo-V2.5-Pro49.746.784.062.892.8N/A80.0%1MOpen weights$0.435$0.87
49MELongCat Flash ChatMeituanLongCat-Flash-Chat49.636.949.375.038.270.3100.0%128KClosed weightsN/AN/A
50ZAGLM 4.5Zhipu AIGLM-4.549.649.361.451.390.0N/A80.0%131.1KOpen weights$0.60$2.2
51NVNemotron 3 UltraNVIDIANemotron 3 Ultra (550B A55B)49.362.982.677.3100.085.3100.0%1MOpen weights$0.50$2.5
52ACQwen3 Next 80B A3BAlibaba Cloud / Qwen TeamQwen3-Next-80B-A3B-Instruct49.036.653.453.018.962.7100.0%131.1KOpen weights$0.50$2
53ACQwen3.6 27BAlibaba Cloud / Qwen TeamQwen3.6-27B49.060.571.871.449.9N/A80.0%262.1KOpen weights$0.60$3.6
54ANClaude Sonnet 4.6AnthropicClaude Sonnet 4.648.772.678.277.7N/AN/A60.0%1MClosed weights$3$15
55ACQwen3.5 27BAlibaba Cloud / Qwen TeamQwen3.5-27B47.957.262.578.059.470.6100.0%262.1KOpen weights$0.30$2.4
56MIMiniMax M2.7MiniMaxMiniMax M2.747.958.4N/AN/AN/AN/A20.0%204.8KOpen weights$0.30$1.2
57MAKimi K2.5Moonshot AIKimi K2.547.366.084.187.367.3N/A80.0%262.1KOpen weights$0.60$3
58ZAGLM 4.7Zhipu AIGLM-4.747.259.779.474.560.6N/A80.0%204.8KOpen weights$0.60$2.2
59MEMuse SparkMetaMuse Spark47.273.268.097.8N/AN/A60.0%N/AClosed weightsN/AN/A
60ACQwen2 72BAlibaba Cloud / Qwen TeamQwen2 72B Instruct46.69.850.924.941.4N/A80.0%N/AClosed weightsN/AN/A
61XIMiMo V2 FlashXiaomiMiMo-V2-Flash46.551.373.063.057.0N/A80.0%262.1KOpen weights$0.14$0.28
62GOGemini 2.5 FlashGoogleGemini 2.5 Flash46.138.170.658.224.871.4100.0%1MClosed weights$0.30$2.5
63MIMAI Thinking 1MicrosoftMAI-Thinking-145.855.174.571.158.838.4100.0%N/AClosed weightsN/AN/A
64GOGemini 3.5 FlashGoogleGemini 3.5 Flash45.779.280.065.2N/AN/A60.0%1MClosed weights$1.5$9
65AMNova 2 LiteAmazonNova 2 Lite45.643.062.063.362.071.4100.0%1MClosed weights$0.33$2.75
66MIMiniMax M3MiniMaxMiniMax M344.871.3N/AN/A100.0N/A40.0%512KOpen weights$0.30$1.2
67GOGemini 3.6 FlashGoogleGemini 3.6 Flash44.579.3N/AN/AN/AN/A20.0%1MClosed weights$1.5$7.5
68ACQwen3.5 35B A3BAlibaba Cloud / Qwen TeamQwen3.5-35B-A3B44.252.061.871.243.854.4100.0%262.1KOpen weights$0.25$2
69BYSeed 2.1 TurboByteDanceSeed 2.1 Turbo42.573.190.985.939.6N/A80.0%N/AClosed weightsN/AN/A
70GOGemma 3 27BGoogleGemma 3 27B39.215.846.837.989.061.1100.0%131.1KClosed weightsN/AN/A
71ACQwen2.5 7BAlibaba Cloud / Qwen TeamQwen2.5 7B Instruct37.66.59.417.258.435.0100.0%131.1KClosed weights$0.175$0.70
72DEDeepSeek-V3.1DeepSeekDeepSeek-V3.136.839.953.666.37.5N/A80.0%131.1KOpen weightsN/AN/A
73GOGemini DiffusionGoogleGemini Diffusion36.83.616.346.13.5N/A80.0%N/AClosed weightsN/AN/A
74MAKimi K2Moonshot AIKimi K2-Instruct-090535.337.255.138.034.563.4100.0%N/AClosed weights$0.60$2.5
75OPGPT-4.5OpenAIGPT-4.533.436.243.891.048.738.7100.0%128KClosed weightsN/AN/A
76GOGemma 3 12BGoogleGemma 3 12B32.411.239.435.474.851.4100.0%131.1KClosed weightsN/AN/A
77OPGPT-4.1OpenAIGPT-4.132.331.938.649.03.529.3100.0%1MClosed weights$2$8
78ACQwen3.6 35B A3BAlibaba Cloud / Qwen TeamQwen3.6-35B-A3B32.355.380.361.640.9N/A80.0%262.1KOpen weights$0.248$1.49
79MIMAI Code 1 FlashMicrosoftMAI-Code-1-Flash32.250.476.233.726.764.3100.0%256KClosed weightsN/AN/A
80NVNemotron 3 SuperNVIDIANemotron 3 Super (120B A12B)31.944.870.060.868.771.4100.0%262.1KOpen weights$0.20$0.80
81MEMuse Glimmer 30BMetaMuse Glimmer-30B31.658.572.540.876.578.6100.0%131.1KOpen weightsN/AN/A
82ZAGLM 4.5 AirZhipu AIGLM-4.5-Air30.941.554.339.686.5N/A80.0%131.1KOpen weights$0.20$1.1
83DEDeepSeek-R1DeepSeekDeepSeek-R1-052830.044.265.270.338.6N/A80.0%131.1KClosed weightsN/AN/A
84ACQwen3 Coder 480B A35BAlibaba Cloud / Qwen TeamQwen3-Coder 480B A35B Instruct29.135.5N/AN/AN/AN/A20.0%262.1KOpen weights$1.5$7.5
85ACQwen2.5 Omni 7BAlibaba Cloud / Qwen TeamQwen2.5-Omni-7B26.110.25.27.844.3100.0100.0%N/AClosed weights$0.10$0.40
86CONorth Mini Code 1.0CohereNorth Mini Code 1.022.537.4N/AN/AN/AN/A20.0%N/AClosed weightsN/AN/A
87MELongCat Flash LiteMeituanLongCat-Flash-Lite21.033.040.354.743.5N/A80.0%256KClosed weightsN/AN/A
88ACQwen2 7BAlibaba Cloud / Qwen TeamQwen2 7B Instruct17.10.03.011.922.445.5100.0%N/AClosed weightsN/AN/A
89GOGemma 3n E4BGoogleGemma 3n E4B Instructed16.90.08.023.419.929.6100.0%32KClosed weightsN/AN/A
90GOGemma 3n E4B LiteRTGoogleGemma 3n E4B Instructed LiteRT Preview16.90.025.726.419.929.6100.0%N/AClosed weightsN/AN/A
91OPGPT-4.1-miniOpenAIGPT-4.1 mini13.124.835.638.65.321.1100.0%1MClosed weights$0.40$1.6
92NVNemotron 3 NanoNVIDIANemotron 3 Nano (30B A3B)12.135.254.340.292.056.7100.0%262.1KOpen weightsN/AN/A
93GOGemma 3 4BGoogleGemma 3 4B10.80.021.713.351.850.4100.0%131.1KClosed weightsN/AN/A
94GOGemini 2.5 Flash LiteGoogleGemini 2.5 Flash-Lite9.819.135.244.811.928.6100.0%1MClosed weights$0.10$0.40
95OPGPT-4oOpenAIGPT-4o8.523.922.835.20.017.4100.0%128KClosed weights$2.5$10
96GOGemma 3n E2BGoogleGemma 3n E2B Instructed7.00.01.811.06.511.4100.0%N/AClosed weightsN/AN/A
97GOGemma 3n E2B LiteRTGoogleGemma 3n E2B Instructed LiteRT (Preview)7.00.09.510.36.511.4100.0%N/AClosed weightsN/AN/A
98GOGemma 3 1BGoogleGemma 3 1B1.00.00.10.66.911.7100.0%N/AClosed weightsN/AN/A

Official PAYG prices appear here. Third-party offers remain on the pricing and model detail pages.

Capability at each price point

Official vendor API prices plotted against the coding metric used on this page. Price remains a separate decision signal.

020406080100$0.1$0.2$0.5$1.0$2.0$5.0$10Coding scoreOfficial API price blend (8:1 input/output), USD / 1M
Efficient frontier69 models with official PAYG prices

Coding Ranking Composition

Vendor concentration and model access among the first 25 ranked products.

Top-model vendor mix

25 models
Anthropic6Alibaba Cloud / Qwen Team5OpenAI4Moonshot AI3DeepSeek2OpenBMB1Amazon1Google1

Access model

Open weights
3
Closed weights
22
Official price available
22

Compare the leaders

Open focused comparisons between the current leader and the nearest practical alternatives.

Claude MythosvsClaude Fable 5Claude MythosvsKimi K3Claude MythosvsStep 3.5 Flash
Overall leaderboardReasoning leaderboardMath leaderboardKnowledge leaderboardInstruction leaderboard

About this leaderboard

Common questions about Best AI for Coding.

What is the best model on Best AI for Coding?

Claude Mythos is currently ranked first with a coding score of 98.7.

How is this leaderboard ranked?

Each model appears once using its current scored version. Category pages use the capability named in the title, while the overall page uses the LLMBoard score.

How many models are included?

This page currently ranks 98 unique model products.

Where does pricing come from?

Main price columns use the model vendor's official standard PAYG API rate. Eligible third-party offers appear only in separately labeled columns, and unavailable official prices display as N/A.

Does Arena affect the score?

No. Arena results are displayed as an independent signal and are not included in the current LLMBoard capability score.