Skip to content

open-source model leaderboards

Last updated: 58m ago

This page is built for high-intent searches like “open LLM leaderboard” and “open source LLM leaderboard”, giving tracked open language models a dedicated ranking and comparison surface.

173

Tracked open LLMs

30

Providers

22

Free endpoints

8

Recent open launches

Top 20 Open-Source Models by Composite Score

Ranked by benchmark performance, capabilities, and context window

LMMarketCap.com

Current Top 25

#ModelProviderScoreMMLUArenaPriceContext
#71DeepSeek V3.2DeepSeek8388.51425$0.269/M164K
#86Gemma 4 31BGoogle81-1453$0.090/M262K
#87Gemma 4 31B (free)Google81-1453Free262K
#89Qwen3.5 397B A17BAlibaba79-1442$0.550/M262K
#90R1 0528DeepSeek7991.51380$0.500/M164K
#103MiMo-V2.6-ProXiaomi79-1480$0.435/M1.1M
#104GLM 5.3Zhipu AI79-1474$0.379/M1.3M
#105GLM 5.3 (batch)Zhipu AI79-1457$0.450/M1.0M
#106GLM 5.2Zhipu AI79-1457$0.650/M1.0M
#107GLM 5.1Zhipu AI78-1465$0.965/M205K
#109GLM 5Zhipu AI78-1457$0.600/M205K
#110GLM 5.3 FlashZhipu AI78-1474$0.040/M1.3M
#112GLM 5.3 Flash (batch)Zhipu AI78-1474$0.060/M1.0M
#113Qwen3.5-122B-A10BAlibaba78-1416$0.260/M262K
#114Gemma 2 27BGoogle7775.2-$0.650/M8K
#115Qwen3.5-27BAlibaba77-1409$0.195/M262K
#120MiMo-V2.5-ProXiaomi76-1467$0.435/M1.1M
#121Qwen3.5-35B-A3BAlibaba76-1394$0.313/M262K
#122Kimi K2.6Moonshot AI76-1461$0.950/M262K
#125MiMo-V2.6-FlashXiaomi75-1454$0.140/M1.0M
#128GLM 4.7Zhipu AI75-1441$0.600/M205K
#129GLM 4.6Zhipu AI75-1424$0.430/M205K
#130GLM 4.5Zhipu AI75-1411$0.600/M131K
#134Hy3Tencent75-1457$0.083/M262K
#140R1DeepSeek7490.81369$0.700/M64K

Top Open Providers

Alibaba

36

DeepSeek

16

Zhipu AI

14

Mistral AI

13

NVIDIA

10

Google

8

Moonshot AI

8

Meta

8

Related Surfaces

Frequently Asked Questions

This page is the tighter “open LLM leaderboard” landing page focused on rankings and table-based comparison, while the broader open-source models page is more explanatory and guide-oriented.

The ranking uses the live composite score, then surfaces benchmark columns, pricing, context window, and release recency so the open-source language model landscape is easier to compare.

Yes. This only includes coding/language models currently marked as open source in the live model catalog. It does not fill the ranking with demo entries.

Open-Source LLM Leaderboard 2026 | LM Market Cap