coding-agent leaderboard · teams
Which team makes the best coding model?
64teams/452models/2026-07-22updated
Every team is only as good as its single best model. So each one here is ranked by that model's composite — a percentile-blended score across every public benchmark we scrape, fair across scales — not by how many models it ships. Flip to Open to rank by best open-weight model.
Team leaderboard
64 teams
#TeamBest model
1Claude Fable 542962GPT-5.6 Sol54953Kimi K319904Muse Spark21855Gemini-3.6-Flash36786Grok 4.517787Nemotron-3 Ultra 550B12758GLM-5.215739Qwen3.6-Plus447310MiroThinker-H127111AI Co-Mathematician27112ERNIE-5.127113Seed2.0 Pro37114seed-2.1-pro-preview16815DeepSeek-V4-Pro-Max276716Step-3.5-Flash56717LongCat-Flash-Chat26618MiniMax M396419MiMo-V2-Pro56420Hunyuan-Hy3116321Agents-A186222Exa Agent36123Amazon-Nova-Chat-11-1056024Mistral Medium 3.1175825MAI-1-Preview85826Parallel Ultra8x65427INTELLECT-315428GLM-5.2 (Max) Z.ai ·25329Thinking Machines Inkling15330Inkling15131Command A (03-2025)64932OLMo-3-32b-think54933Yi-Lightning54934Athene-v2-Chat-72B24935Sarvam-105B24736Perplexity Agent Advanced54637OpenSeeker-v224438QED-Nano14139Tongyi DeepResearch54140GLM-4.7-Flash14041Jamba-1.5-Large24042laguna-m.124043Tavily + GPT-5.4 harness14044Reka-Core-2024090444045Gemma-2-9B-it-SimPO13846Granite-3.1-8B-Instruct53547InternLM2.5-20B-chat13448KAT-Coder-Pro-V113349WebExplorer-8B (RL)13350Starling-LM-7B-beta13251DeepDive-32B13252Zephyr-ORPO-141b-A35b-v0.123253DBRX-Instruct-Preview13254OpenChat-3.5-010623055Starling-LM-7B-alpha12956Nous-Hermes-2-Mixtral-8x7B-DPO22957Snowflake Arctic Instruct12858Vicuna-33B12759mercury-212760SOLAR-10.7B-Instruct-v1.012761pplx-70B-online12662MPT-30B-chat12663Dolphin-2.2.1-Mistral-7B12664K2 Think V2113
Anthropic
OpenAI
Moonshot AI
open
Meta
Google
xAI
NVIDIA
open
Z.ai
open
Alibaba
MiroMind
Google DeepMind
Baidu
ByteDance
Bytedance
DeepSeek
open
StepFun
open
Meituan
open
MiniMax
open
Xiaomi
Tencent
Academic Research
Exa
Amazon
Mistral AI
Microsoft
Parallel
Prime Intellect
open
MIT
Thinky
Thinking Machines
Cohere
Ai2
open
01 AI
NexusFlow
Sarvam AI
Perplexity
PolarSeeker
LM-Provers
Alibaba Cloud / Tongyi Lab
Zhipu AI
AI21 Labs
open
Poolside
open
Tavily
Reka AI
Princeton
open
IBM
open
InternLM
Proprietary
HKUST NLP Group
Nexusflow
open
THUDM / Tsinghua University
HuggingFace
open
Databricks
OpenChat
open
UC Berkeley
NousResearch
open
Snowflake
open
LMSYS
Inception AI
Upstage AI
Perplexity AI
MosaicML
Cognitive
open
MBZUAI Institute of Foundation Models
A team's score is the composite of its top-ranked model — shipping more models never helps unless one is genuinely better. Best model → opens that model's full profile.