Meta

Code Llama 34B Instruct

Code Llama 34B Instruct is an open-weight model from Meta. It ranks #386 of 351 on the LMArena text leaderboard with a rating of 1066.

LMArena text1066+0 in 30 days
Rank#386/351
95% interval1057–1074
Votes7.4K
Developer
Meta
Released
Sep 5, 2023
Context window
—
Price in / out, per 1M tokens
—
Weights
Open · Llama 2 Community
Inputs
—
Reasoning
—
Tool use
—
Code Llama 34B Instruct, LMArena text rating over time
9901015104010651090Sep 23Jun 24Mar 25Jan 26Oct 26
LatestCode Llama 34B Instruct 1066

The rating LMArena published at each update since Sep 5, 2023. Ratings move as votes come in and new models join.

LMArena, by category

LeaderboardRatingRankVotes
TextLMArena1066386 / 3517.4K
CodingLMArena1046385 / 346853
MathLMArena1056377 / 339770
Creative writingLMArena1031391 / 3491.5K
Instruction followingLMArena1028392 / 3512.3K
Hard promptsLMArena1032388 / 3511.5K
Multi-turnLMArena1015390 / 3491.2K
Long queriesLMArena1013385 / 330320
Legal and governmentIndustries1064371 / 325383
Medicine and healthcareIndustries1026370 / 325340
Business and financeIndustries1034375 / 344639
ChineseLanguages977382 / 328249

LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.

Compare Code Llama 34B Instruct

Meta

Meta’s AI research publishes the Llama family, among the most downloaded open-weight models. Founded 2013 (FAIR), based in Menlo Park. ai.meta.com

Questions

Who makes Code Llama 34B Instruct?

Code Llama 34B Instruct is made by Meta, founded 2013 (FAIR) and based in Menlo Park.

How does Code Llama 34B Instruct rank?

#386 of 351 on LMArena’s text leaderboard, rated 1066 (95% interval 1057–1074) from 7,366 votes, as of Oct 22, 2026.

Is Code Llama 34B Instruct open source?

Code Llama 34B Instruct has open weights under the Llama 2 Community license.

Sources

Every number on this page comes from these sources; models without a published number show none. Download the data. Cite as “Nexus Explorer, nexus.inc/models”.