Meta, open weights
Llama 13b
Llama 13b by Meta ranks 348th of 354 ranked models on the Noometry Index as of October 2026, with a score of 24.4. Its strongest category is math, where it ranks 256th.
Last verified
Specifications
- Noometry rank
- #348 of 354
- Index score
- 24.4
- Evidence
- Confirmed 21 results
- Provider
Meta- Released
- February 24, 2023
- 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.
- Coding 21.4
- Reasoning 14.0
- Math 26.7
- Multilingual 16.6
- Instruction Following 36.7
- Writing & Preference 13.8
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 21.4 | #337 | 1 |
| Reasoning | 14.0 | #329 | 1 |
| Math | 26.7 | #256 | 1 |
| Multilingual | 16.6 | #297 | 1 |
| Instruction Following | 36.7 | #305 | 1 |
| Writing & Preference | 13.8 | #312 | 3 |
Strengths and weaknesses
Categories where Llama 13b places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Writing & Preference | 13.8 | −40.0 | #312 of 312, top 100% |
| Instruction Following | 36.7 | −34.6 | #305 of 305, top 100% |
| Multilingual | 16.6 | −30.8 | #297 of 297, top 100% |
Closest competitors
The models ranked just above and below Llama 13b. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Llama 3-8B | #344 | 25.5 | — | — | Compare |
| Claude 2.1 | #345 | 25.2 | — | — | Compare |
| Claude 2 | #346 | 25.0 | — | — | Compare |
| DeepSeek LLM 67B | #347 | 24.9 | — | — | Compare |
| Llama 2-70B | #349 | 24.4 | — | — | Compare |
| GPT-3.5-turbo | #350 | 23.2 | $0.75 | — | Compare |
| Mistral 7B | #351 | 23.0 | $0.25 | — | Compare |
| Llama 3.1-8B | #352 | 23.0 | $0.0575 | — | 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.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Coding | 683 | #294 of 294, top 100% | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 728 | #297 of 297, top 100% | LMArena | 2026-10-08 | |
| BIG-Bench Hard | 37.9% | #23 of 27, top 86% | Epoch AI | ||
| Epoch Capabilities Index | 100.58 | #203 of 213, top 96% | Epoch AI | 2023-02-24 | |
| HellaSwag | 79.2% | #18 of 29, top 63% | Epoch AI | ||
| LAMBADA | 75.2% | #5 of 9, top 56% | Epoch AI | ||
| PIQA | 80.1% | #22 of 27, top 82% | Epoch AI | ||
| WinoGrande | 73% | #27 of 43, top 63% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 838 | #285 of 285, top 100% | LMArena | 2026-10-08 | |
| GSM8K | 20.6% | #34 of 38, top 90% | Epoch AI |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| ARC (AI2) Challenge | 52.7% | #27 of 39, top 70% | Epoch AI | ||
| BoolQ | 78.7% | #16 of 23, top 70% | Epoch AI | ||
| MMLU | 47.7% | #70 of 81, top 87% | Epoch AI | ||
| OpenBookQA | 56.4% | #16 of 19, top 85% | Epoch AI | ||
| TriviaQA | 77.9% | #14 of 25, top 57% | Epoch AI |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| ScienceQA | 43.3% | #5 of 6, top 84% | Epoch AI |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 819 | #297 of 297, top 100% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 781 | #298 of 298, top 100% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 834 | #297 of 297, top 100% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 794 | #295 of 295, top 100% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 753 | #294 of 295, top 100% | LMArena | 2026-10-08 |
Compare Llama 13b
- Llama 13b vs DeepSeek LLM 67B
- Llama 13b vs Llama 2-70B
- Llama 13b vs Claude 2
- Llama 13b vs GPT-3.5-turbo
- Llama 13b vs Claude 2.1
- Llama 13b vs Mistral 7B
- Llama 13b vs GPT-6 Astra
- Llama 13b vs Claude Fable 5.1
- Llama 13b vs Gemini 3.8 Flash
- Llama 13b vs Kimi K3
- Llama 13b vs Grok 4.6
- Llama 13b vs Qwen3.8 Max
- Llama 13b vs GLM-5.3
- Llama 13b vs DeepSeek V4 Pro
Other Meta models
- Muse Spark 1.354.8
- Muse Spark50.6
- Muse Spark 1.250.3
- Muse Spark 1.149.9
- Muse Glimmer41.7
- Codellama 70b Instruct33.7
- Llama 4 Maverick30.9
- Codellama 34b Instruct30.8
Frequently asked questions
How good is Llama 13b?
Llama 13b by Meta ranks 348th of 354 ranked models on the Noometry Index as of October 2026, with a score of 24.4. Its strongest category is math, where it ranks 256th.
Is Llama 13b open source?
Yes. Llama 13b's weights are downloadable; check the license for commercial terms.
What are Llama 13b's strengths and weaknesses?
Relative to other ranked models, Llama 13b places best in math, reasoning, coding and lowest in writing & preference, instruction following, multilingual.
What is Llama 13b best at?
Its best category is math, where it ranks 256th on Noometry.