Meta, open weights
Llama 2-13B
Llama 2-13B by Meta ranks 309th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.6. Its strongest category is math, where it ranks 229th.
Last verified
Specifications
- Noometry rank
- #309 of 354
- Index score
- 29.6
- Evidence
- Confirmed 32 results
- Provider
Meta- Released
- July 18, 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 30.9
- Reasoning 12.8
- Math 31.1
- Knowledge 28.1
- Multilingual 26.5
- Instruction Following 53.3
- Long Context 32.3
- Writing & Preference 29.8
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 30.9 | #291 | 1 |
| Reasoning | 12.8 | #337 | 3 |
| Math | 31.1 | #229 | 1 |
| Knowledge | 28.1 | #249 | 1 |
| Multilingual | 26.5 | #279 | 1 |
| Instruction Following | 53.3 | #287 | 1 |
| Long Context | 32.3 | #269 | 1 |
| Writing & Preference | 29.8 | #289 | 3 |
Strengths and weaknesses
Categories where Llama 2-13B 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 |
|---|---|---|---|
| Reasoning | 12.8 | −10.8 | #337 of 350, top 97% |
| Instruction Following | 53.3 | −18.0 | #287 of 305, top 95% |
| Multilingual | 26.5 | −20.9 | #279 of 297, top 94% |
Closest competitors
The models ranked just above and below Llama 2-13B. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Phi 3 Mini 128k Instruct | #305 | 29.7 | — | — | Compare |
| phi-3-medium 14B | #306 | 29.7 | — | — | Compare |
| Gemma 2B | #307 | 29.6 | — | — | Compare |
| Llama 3.1-70B | #308 | 29.6 | $0.40 | — | Compare |
| Claude 3 Opus | #310 | 29.5 | — | — | Compare |
| DBRX | #311 | 29.4 | — | — | Compare |
| Gemma 2 27B | #312 | 29.4 | $0.65 | — | Compare |
| Gemma 1.1 2b IT | #313 | 29.3 | — | — | 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 | 1062 | #281 of 294, top 96% | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Chess Puzzles | 0% | #118 of 129, top 92% | Epoch AI | 2026-08-28 | |
| LMArena Hard Prompts | 1051 | #281 of 297, top 95% | LMArena | 2026-10-08 | |
| DTBench | 42.2% | #150 of 151, top 100% | Epoch AI | ||
| BIG-Bench Hard | 58.2% | #15 of 27, top 56% | Epoch AI | ||
| BIG-Bench Hard | 47% | Epoch AI | |||
| Epoch Capabilities Index | 106.17 | #196 of 213, top 93% | Epoch AI | 2023-07-18 | |
| HellaSwag | 80.7% | #17 of 29, top 59% | Epoch AI | ||
| LAMBADA | 76.5% | #4 of 9, top 45% | Epoch AI | ||
| PIQA | 80.8% | #20 of 27, top 75% | Epoch AI | ||
| WinoGrande | 72.8% | #29 of 43, top 68% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1065 | #275 of 285, top 97% | LMArena | 2026-10-08 | |
| GSM8K | 34.3% | Epoch AI | |||
| GSM8K | 36.9% | #28 of 38, top 74% | Epoch AI |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1030 | #268 of 273, top 99% | LMArena | 2026-10-08 | |
| ARC (AI2) Challenge | 60.3% | #23 of 39, top 59% | Epoch AI | ||
| BoolQ | 82.4% | #15 of 23, top 66% | Epoch AI | ||
| MMLU | 50.9% | Epoch AI | |||
| MMLU | 55.6% | #68 of 81, top 84% | Epoch AI | ||
| OpenBookQA | 57% | #14 of 19, top 74% | Epoch AI | ||
| TriviaQA | 79.6% | #12 of 25, top 48% | Epoch AI |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| ScienceQA | 55.8% | #4 of 6, top 67% | Epoch AI |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1024 | #279 of 297, top 94% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1001 | #278 of 285, top 98% | LMArena | 2026-10-08 | |
| LMArena French | 1044 | #219 of 223, top 99% | LMArena | 2026-10-08 | |
| LMArena German | 1009 | #226 of 231, top 98% | LMArena | 2026-10-08 | |
| LMArena Japanese | 894 | #210 of 211, top 100% | LMArena | 2026-10-08 | |
| LMArena Korean | 953 | #208 of 213, top 98% | LMArena | 2026-10-08 | |
| LMArena Russian | 1055 | #266 of 283, top 94% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1087 | #218 of 226, top 97% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1045 | #284 of 298, top 96% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1064 | #274 of 291, top 95% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1084 | #277 of 297, top 94% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1047 | #278 of 295, top 95% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1050 | #277 of 295, top 94% | LMArena | 2026-10-08 |
Compare Llama 2-13B
- Llama 2-13B vs Llama 13b
- Llama 2-13B vs Llama 3.1-70B
- Llama 2-13B vs Claude 3 Opus
- Llama 2-13B vs Gemma 2B
- Llama 2-13B vs DBRX
- Llama 2-13B vs phi-3-medium 14B
- Llama 2-13B vs Gemma 2 27B
- Llama 2-13B vs GPT-6 Astra
- Llama 2-13B vs Claude Fable 5.1
- Llama 2-13B vs Gemini 3.8 Flash
- Llama 2-13B vs Kimi K3
- Llama 2-13B vs Grok 4.6
- Llama 2-13B vs Qwen3.8 Max
- Llama 2-13B vs GLM-5.3
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 2-13B?
Llama 2-13B by Meta ranks 309th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.6. Its strongest category is math, where it ranks 229th.
Is Llama 2-13B open source?
Yes. Llama 2-13B's weights are downloadable; check the license for commercial terms.
What are Llama 2-13B's strengths and weaknesses?
Relative to other ranked models, Llama 2-13B places best in math, knowledge, coding and lowest in reasoning, instruction following, multilingual.
What is Llama 2-13B best at?
Its best category is math, where it ranks 229th on Noometry.