Noometry

Meta, open weights

Codellama 70b Instruct

Codellama 70b Instruct by Meta ranks 237th of 354 ranked models on the Noometry Index as of October 2026, with a score of 33.7. Its strongest category is coding, where it ranks 193rd.

Last verified

Noometry rank
#237 of 354
Index score
33.7
Evidence
Confirmed 7 results
Provider
Meta
Released
Unknown
Weights
Open weights
Reasoning
Unknown
Context window
—
Max output
—
Input price
Not listed
Output price
Not listed
Blended price
Not listed
Output speed
Not measured
Value
Not ranked
Knowledge cutoff
Unknown

Category scores

Each category score combines every public result we have in that category.

  1. Coding 37.6
  2. Reasoning 20.1
  3. Multilingual 24.8
  4. Instruction Following 51.9
  5. Writing & Preference 33.4
CategoryScoreRankResults
Coding37.6#1932
Reasoning20.1#2421
Multilingual24.8#2881
Instruction Following51.9#2931
Writing & Preference33.4#2771

Strengths and weaknesses

Categories where Codellama 70b Instruct places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Coding37.6−1.2#193 of 340, top 57%
Reasoning20.1−3.5#242 of 350, top 70%

Weakest categories

CategoryScorevs medianRank
Multilingual24.8−22.6#288 of 297, top 97%
Instruction Following51.9−19.4#293 of 305, top 97%

Closest competitors

The models ranked just above and below Codellama 70b Instruct. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Devstral Small 2505#23334.3$0.1588Compare
Qwen1.5-110B#23434.2——Compare
o1-mini#23534.0——Compare
Qwen3.5-9B#23633.8$0.11—Compare
Qwen3 8B#23833.7$0.31—Compare
Grok-2 (Dec 2024)#23933.7——Compare
GPT-4.1 mini#24033.6$0.7086Compare
GPT-5 Nano#24133.5$0.144Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
BigCodeBench Instruct40.7%#31 of 64, top 49%BigCodeBench2023-08-25
BigCodeBench Complete44%BigCodeBench2023-08-25
BigCodeBench Complete49.6%#36 of 66, top 55%BigCodeBench2023-08-25
HumanEval+65.9%#23 of 45, top 52%EvalPlus
HumanEval+50.6%EvalPlus

Reasoning

BenchmarkScorePositionSettingSourceDate
LMArena Hard Prompts1052#280 of 297, top 95%LMArena2026-10-08

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English992#288 of 297, top 97%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1024#288 of 298, top 97%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1057#284 of 297, top 96%LMArena2026-10-08

Compare Codellama 70b Instruct

Other Meta models

Frequently asked questions

How good is Codellama 70b Instruct?

Codellama 70b Instruct by Meta ranks 237th of 354 ranked models on the Noometry Index as of October 2026, with a score of 33.7. Its strongest category is coding, where it ranks 193rd.

Is Codellama 70b Instruct open source?

Yes. Codellama 70b Instruct's weights are downloadable; check the license for commercial terms.

What are Codellama 70b Instruct's strengths and weaknesses?

Relative to other ranked models, Codellama 70b Instruct places best in coding, reasoning and lowest in multilingual, instruction following.

What is Codellama 70b Instruct best at?

Its best category is coding, where it ranks 193rd on Noometry.