llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1367 models808 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 Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Capability ranking

Best AI for Coding

Use this coding AI model leaderboard to compare the current ranking from the LLMBoard Coding Score, aggregated across eligible coding and tool-use benchmarks.

Updated 2026-10-22

On this page

  • Ranking
  • Overview
  • Leaders
  • Capability
  • Value
  • Composition
  • Top models
  • FAQ

Coding Model Leaderboard Ranking

This leaderboard ranking orders models by their LLMBoard Coding Score aggregated from eligible benchmark evidence.

30 of 132 rows
Columns

Show columns

Sort by
Rank
Model
LLMBoard Coding Score
Official input / 1M
Official output / 1M
Output speed
Context
Rank01ModelANClaude MythosAnthropicLLMBoard Coding Score97.08Official input / 1MN/AOfficial output / 1MN/AOutput speedN/AContextN/A
Rank02ModelANClaude Opus 5.5AnthropicLLMBoard Coding Score96.24Official input / 1M$4Official output / 1M$20Output speed12.33 tok/sContext1M
Rank03ModelMEMuse Spark 1.3MetaLLMBoard Coding Score92.38Official input / 1M$1.25Official output / 1M$4.25Output speedN/AContext1M
Rank04ModelANClaude Fable 5AnthropicLLMBoard Coding Score89.03Official input / 1M$10Official output / 1M$50Output speedN/AContext1M
Rank05ModelANClaude Sonnet 5.5AnthropicLLMBoard Coding Score88.90Official input / 1M$2Official output / 1M$10Output speed42.00 tok/sContext1M
Rank06ModelGOGemini 3.8 FlashGoogleLLMBoard Coding Score86.46Official input / 1M$0.75Official output / 1M$3.75Output speed55.66 tok/sContext1M
Rank07ModelMEMuse Wonder FullMetaLLMBoard Coding Score85.81Official input / 1MN/AOfficial output / 1MN/AOutput speedN/AContextN/A
Rank08ModelOPGPT-6-AstraOpenAILLMBoard Coding Score85.15Official input / 1M$10Official output / 1M$50Output speedN/AContext1.1M
Rank09ModelOPGPT-5.6-SolOpenAILLMBoard Coding Score81.50Official input / 1M$4Official output / 1M$20Output speed25.46 tok/sContext1.1M
Rank10ModelFAEmber 1Fireworks AILLMBoard Coding Score79.21Official input / 1M$3Official output / 1M$15Output speedN/AContext1M
Rank11ModelANClaude Opus 4.8AnthropicLLMBoard Coding Score78.09Official input / 1M$5Official output / 1M$25Output speed42.00 tok/sContext1M
Rank12ModelANClaude Haiku 5.5AnthropicLLMBoard Coding Score77.14Official input / 1M$0.10Official output / 1M$0.50Output speedN/AContext1M
Rank13ModelANClaude Opus 5AnthropicLLMBoard Coding Score76.14Official input / 1M$5Official output / 1M$25Output speedN/AContext1M
Rank14ModelDEDeepSeek-V4-ProDeepSeekLLMBoard Coding Score75.82Official input / 1M$0.66Official output / 1M$1.98Output speedN/AContext1M
Rank15ModelMAKimi K3Moonshot AILLMBoard Coding Score75.71Official input / 1M$3Official output / 1M$15Output speedN/AContext1M
Rank16ModelACQwen3.7 MaxAlibaba Cloud / Qwen TeamLLMBoard Coding Score75.31Official input / 1M$2.5Official output / 1M$7.5Output speedN/AContext1M
Rank17ModelMEMuse WonderMetaLLMBoard Coding Score71.59Official input / 1M$4Official output / 1M$20Output speedN/AContext1M
Rank18ModelRABeam 1.0Reflection AILLMBoard Coding Score71.34Official input / 1MN/AOfficial output / 1MN/AOutput speedN/AContext1M
Rank19ModelANClaude Sonnet 5AnthropicLLMBoard Coding Score71.22Official input / 1M$2Official output / 1M$10Output speed42.00 tok/sContext1M
Rank20ModelDEDeepSeek-V4.1DeepSeekLLMBoard Coding Score70.93Official input / 1M$0.15Official output / 1M$0.60Output speedN/AContext1M
Rank21ModelMIMiniMax M3.1 FlashMiniMaxLLMBoard Coding Score70.83Official input / 1M$0.15Official output / 1M$0.60Output speedN/AContext1M
Rank22ModelANClaude Opus 4.6AnthropicLLMBoard Coding Score70.44Official input / 1M$5Official output / 1M$25Output speed42.00 tok/sContext1M
Rank23ModelACQwen3.8 FlashAlibaba Cloud / Qwen TeamLLMBoard Coding Score68.41Official input / 1M$0.15Official output / 1M$0.47Output speedN/AContext1M
Rank24ModelOPMiniCPM SALAOpenBMBLLMBoard Coding Score68.34Official input / 1MN/AOfficial output / 1MN/AOutput speedN/AContextN/A
Rank25ModelACQwen3.8 Flash NextAlibaba Cloud / Qwen TeamLLMBoard Coding Score68.09Official input / 1MN/AOfficial output / 1MN/AOutput speedN/AContextN/A
Rank26ModelACQwen2.5 Coder 32BAlibaba Cloud / Qwen TeamLLMBoard Coding Score67.80Official input / 1MN/AOfficial output / 1MN/AOutput speed44.00 tok/sContext128K
Rank27ModelOPGPT-5.6-TerraOpenAILLMBoard Coding Score67.74Official input / 1M$2Official output / 1M$12Output speed43.35 tok/sContext1.1M
Rank28ModelGOGemini 3.7 FlashGoogleLLMBoard Coding Score67.72Official input / 1M$0.75Official output / 1M$3.75Output speed409.96 tok/sContext1M
Rank29ModelMAKimi K2.6Moonshot AILLMBoard Coding Score66.90Official input / 1M$0.95Official output / 1M$4Output speedN/AContext262.1K
Rank30ModelANClaude Opus 4.7AnthropicLLMBoard Coding Score66.86Official input / 1M$5Official output / 1M$25Output speed42.00 tok/sContext1M

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

What this leaderboard says

Key findings from the current coding leaderboard ranking and its supporting benchmark coverage.

Ranked models132
Vendors29
Open-weight models77
Official prices76

Claude Mythos leads this page at 97.08, 0.84 points ahead of Claude Opus 5.5.

DeepSeek-V4-Pro is the highest-ranked open-weight option at #14. Claude Haiku 5.5 has the lowest official input price among ranked models.

Coding Leaderboard Leaders

The leading coding scores in this benchmark-backed ranking, with the axis focused on the competitive leaderboard range.

Top coding models

Coding Benchmark Profile

Compare coding benchmark strength with each model's broader capability score and leaderboard position.

ModelReasoningKnowledgeMathCodingInstruction
Claude MythosAnthropicN/A99.31N/A97.08N/A
Claude Opus 5.5AnthropicN/A93.52N/A96.24N/A
Muse Spark 1.3Meta92.0391.75N/A92.3893.70
Claude Fable 5Anthropic94.7197.74N/A89.0376.13
Claude Sonnet 5.5AnthropicN/A97.44N/A88.90N/A
42.9357.7072.4787.23102.00-7.9720.9149.7978.67107.55LLMBoard Coding ScoreLLMBoard Overall Score
80 models with comparable dataOpen a model by selecting its logo

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$10LLMBoard Coding ScoreOfficial API price blend (8:1 input/output), USD / 1M
Efficient frontier76 models with official PAYG prices

Coding Leaderboard Composition

Vendor concentration and model access among the first 25 products in the ranking.

Top-model vendor mix

25 models
Anthropic9
Meta3
Alibaba Cloud / Qwen Team3
OpenAI2
DeepSeek2
Google1
Fireworks AI1
Moonshot AI1

Access model

Open weights
7
Closed weights
18
Official price available
20

The Top AI Models for Coding

A data-backed look at the first five models in this coding leaderboard ranking, including benchmark context, price and output speed where available.

About this leaderboard

Common questions about the Best AI for Coding leaderboard, benchmark evidence and ranking method.

What is the best model on Best AI for Coding?

Claude Mythos is currently ranked first with a coding score of 97.08.

Which three AI models lead this capability ranking?

The current leaders are Claude Mythos (97.08 LLMBoard Coding Score), Claude Opus 5.5 (96.24 LLMBoard Coding Score), and Muse Spark 1.3 (92.38 LLMBoard Coding Score).

Which ranked model has the lowest official input price?

Claude Haiku 5.5 has the lowest current official input price among ranked models at $0.1 per 1M tokens.

Which ranked models have the highest measured output speed?

The fastest matched records are Llama 4 Scout (776.10 tok/s via Groq), Llama 4 Maverick (638.70 tok/s via Sambanova), and Gemini 3.7 Flash (409.96 tok/s via Google).

Which open-weight model ranks highest?

DeepSeek-V4-Pro is the highest-ranked open-weight model at rank #14.

AA Omniscience Accuracy65.35%Claude Fable 588 compared models
AA CritPt32.29%GPT-5.6-Sol88 compared models
AA HLE Text No Tools55.47%Claude Fable 588 compared models
AA GPQA Diamond96.26%GPT-6-Astra88 compared models
AA LCR v1.188.67%Kimi K387 compared models
AA IFBench82.86%MiniMax M360 compared models
AA AIME 202596.67%DeepSeek-V3.220 compared models
AA SciCode Subtasks61.00%Claude Fable 561 compared models
Which model offers the longest context in this ranking?

Llama 4 Scout has the largest listed context window at 10M tokens.

How is this leaderboard ranked?

Each model appears once using its current scored version. The leaderboard ranking follows the capability named in the title, while the overall page uses the LLMBoard score aggregated from eligible benchmark evidence.

How many models are included?

This page currently ranks 132 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.

Top coding modelClaude Mythos97.08 coding score
Best open-weight modelDeepSeek-V4-ProRank #14
Lowest official inputClaude Haiku 5.5$0.1 / 1M
Largest contextLlama 4 Scout10M tokens

Ranking basisThis coding AI model leaderboard uses the coding capability score shown on this page. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    AN
    Claude MythosAnthropic
    LLMBoard Coding Score
    97.08

    Strengths

    • Ranks #1 with a 97.08 LLMBoard Coding Score

    Considerations

    • 40% benchmark coverage
    • Weights are not marked as open
  2. 02
    AN
    Claude Opus 5.5Anthropic
    LLMBoard Coding Score
    96.24
    Price
    $4 input / $20 output per 1M tokens
    Speed
    12.33 tok/s via Anthropic

    Strengths

    • Ranks #2 with a 96.24 LLMBoard Coding Score
    • 1M maximum context tokens

    Considerations

    • 40% benchmark coverage
    • Weights are not marked as open
  3. 03
    ME
    Meta
    LLMBoard Coding Score
    92.38
    Price
    $1.3 input / $4.3 output per 1M tokens

    Strengths

    • Ranks #3 with a 92.38 LLMBoard Coding Score
    • Lowest official input price among the top models
    • 1M maximum context tokens

    Considerations

    • Weights are not marked as open
  4. 04
    AN
    Anthropic
    LLMBoard Coding Score
    89.03
    Price
    $10 input / $50 output per 1M tokens

    Strengths

    • Ranks #4 with a 89.03 LLMBoard Coding Score
    • 1M maximum context tokens

    Considerations

    • Weights are not marked as open
  5. 05
    AN
    Anthropic
    LLMBoard Coding Score
    88.90
    Price
    $2 input / $10 output per 1M tokens
    Speed
    42.00 tok/s via Anthropic

    Strengths

    • Ranks #5 with a 88.90 LLMBoard Coding Score
    • 1M maximum context tokens

    Considerations

    • 40% benchmark coverage
    • Weights are not marked as open

Selection summary

Best AI Models for Coding

Claude Mythos is currently the best-ranked LLM for coding with a 97.08 coding score. The score is a relative ranking signal, so price, speed, context and evidence coverage should still be checked separately.

Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.

Muse Spark 1.3
Claude Fable 5
Claude Sonnet 5.5
Capability rank #1Claude Mythos97.08
Capability rank #2Claude Opus 5.512.33 tok/s via Anthropic
Capability rank #3Muse Spark 1.3$1.3 input / $4.3 output per 1M tokens