Arena coding leaderboard

Arena coding standings (208 models)

Sorted by published score, one row per model. Source: Arena (LMArena).

How ModelCap uses Arena coding

Arena coding ranks models by human preference rating on coding prompts. ModelCap ingests the board as published, matches each entry to a catalogue model with a reviewed identity, and shows the source's score, interval and rank unchanged. Not on its own. The ModelCap Index combines several public capability sources with published uncertainty; Arena coding contributes as coding evidence where a model has an admitted result. The methodology page documents the weighting. Read the methodology and identity rules.

Other benchmark leaderboards

• Arena text leaderboardClaude Opus 4.6 leads 208 models at 1505
• LMArena Agent leaderboardClaude Fable 5.1 leads 40 models at 14.6%
• ARC-AGI-2 leaderboardGPT-6 Astra leads 67 models at 95.0%
• ARC-AGI-3 leaderboardGPT-6 Astra leads 17 models at 62.7%
• SWE-bench leaderboardGemini 3 Flash Preview leads 27 models at 75.8%
• BFCL V4 function-calling leaderboardClaude Opus 4.5 leads 44 models at 77.5
• Artificial Analysis Intelligence IndexClaude Opus 5.5 leads 85 models at 57.6
• Terminal-Bench 2.1 (Artificial Analysis run)Claude Fable 5.1 leads 106 models at 91.4%
• τ²-Bench Telecom (Artificial Analysis run)GLM 5.2 leads 154 models at 99.1%
• Humanity's Last Exam (Artificial Analysis run)Claude Opus 5.5 leads 216 models at 61.4%
• Terminal-Bench 4.0 leaderboardGPT-6 Astra leads 15 models at 58.2%
• Terminal-Bench 2.1 Terminus 2 leaderboardClaude Fable 5 leads 3 models at 80.5
• WildClawBench OpenClaw leaderboardGPT-5.6 Sol leads 29 models at 67.2

Explore further

• AI model rankingsThe live ModelCap Index across every board
• All benchmark leaderboards14 public boards
• MethodologyHow boards become the ModelCap Index
• Kimi K3 vs MiMo-V2.6-ProHead-to-head on Arena coding, price and context
• Kimi K3 vs GPT-6 AstraHead-to-head on Arena coding, price and context
• Kimi K3 vs Muse Spark 1.3Head-to-head on Arena coding, price and context
• MiMo-V2.6-Pro vs GPT-6 AstraHead-to-head on Arena coding, price and context
• Anthropic modelsPublisher of the Arena coding leader