Meta, open weights
Code Llama 70b Instruct
Code Llama 70b Instruct by Meta ranks 267th of 368 ranked models on the Noometry Index as of November 2026, with a score of 33.7. Its strongest category is reasoning, where it ranks 253rd.
Last verified
Specifications
- Noometry rank
- #267 of 368
- Index score
- 33.7
- Evidence
- Reported 4 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.
- Reasoning 22.3
- Multilingual 23.8
- Instruction Following 51.6
- Writing & Preference 33.6
| Category | Score | Rank | Results |
|---|---|---|---|
| Reasoning | 22.3 | #253 | 1 |
| Multilingual | 23.8 | #285 | 1 |
| Instruction Following | 51.6 | #296 | 1 |
| Writing & Preference | 33.6 | #281 | 1 |
Strengths and weaknesses
Categories where Code Llama 70b Instruct places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Reasoning | 22.3 | −3.8 | #253 of 349, top 73% |
| Writing & Preference | 33.6 | −20.0 | #281 of 317, top 89% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Multilingual | 23.8 | −23.0 | #285 of 294, top 97% |
| Instruction Following | 51.6 | −19.4 | #296 of 308, top 97% |
Closest competitors
The models ranked just above and below Code Llama 70b Instruct. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Gemma 2 2b IT | #263 | 33.9 | — | — | Compare |
| Phi 3 Medium 4k Instruct | #264 | 33.9 | — | — | Compare |
| GPT-4.1 mini | #265 | 33.8 | $0.70 | 86 | Compare |
| Gemini 1.5 Flash (May 2024) | #266 | 33.8 | — | — | Compare |
| GPT-5 Nano | #268 | 33.6 | $0.14 | 4 | Compare |
| Qwen1.5-14B | #269 | 33.6 | — | — | Compare |
| Laguna M.1 | #270 | 33.5 | — | — | Compare |
| gpt-oss-20b | #271 | 33.4 | $0.055 | 96 | Compare |
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.
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1052 | #277 of 294, top 95% | Code Llama 70B Instruct | LMArena | 2026-10-28 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 992 | #285 of 294, top 97% | Code Llama 70B Instruct | LMArena | 2026-10-28 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1024 | #284 of 294, top 97% | Code Llama 70B Instruct | LMArena | 2026-10-28 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1057 | #281 of 294, top 96% | Code Llama 70B Instruct | LMArena | 2026-10-28 |
Compare Code Llama 70b Instruct
- Code Llama 70b Instruct vs Gemini 1.5 Flash (May 2024)
- Code Llama 70b Instruct vs GPT-5 Nano
- Code Llama 70b Instruct vs GPT-4.1 mini
- Code Llama 70b Instruct vs Qwen1.5-14B
- Code Llama 70b Instruct vs Phi 3 Medium 4k Instruct
- Code Llama 70b Instruct vs Laguna M.1
- Code Llama 70b Instruct vs GPT-6 Astra
- Code Llama 70b Instruct vs Claude Opus 5.5
- Code Llama 70b Instruct vs Gemini 4 Argon
- Code Llama 70b Instruct vs Kimi K3
- Code Llama 70b Instruct vs DeepSeek V4.1 Flash
- Code Llama 70b Instruct vs Qwen3.8 Max
- Code Llama 70b Instruct vs Grok 4.6
- Code Llama 70b Instruct vs Doubao Seed Evolving
Other Meta models
- Muse Wonder57.4
- Muse Spark 1.354.9
- Muse Spark51.2
- Muse Spark 1.251.2
- Muse Spark Open51.0
- Muse Spark 1.150.6
- Muse Glimmer42.5
- Code Llama 34b Instruct32.0
Frequently asked questions
How good is Code Llama 70b Instruct?
Code Llama 70b Instruct by Meta ranks 267th of 368 ranked models on the Noometry Index as of November 2026, with a score of 33.7. Its strongest category is reasoning, where it ranks 253rd.
Is Code Llama 70b Instruct open source?
Yes. Code Llama 70b Instruct's weights are downloadable; check the license for commercial terms.
What are Code Llama 70b Instruct's strengths and weaknesses?
Relative to other ranked models, Code Llama 70b Instruct places best in reasoning, writing & preference and lowest in multilingual, instruction following.
What is Code Llama 70b Instruct best at?
Its best category is reasoning, where it ranks 253rd on Noometry.