MetaLLaMA-13B
LLaMA-13B is a Meta proprietary model, released 24 Feb 2023. It is not yet ranked: 4 independent results so far, and the index needs at least five across two categories. Last measured 22 Oct 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Full answer
- –
- Cost per run
- –
- Released
- 24 Feb 2023
- Reasoning5
- Coding5
- Maths6
- Human preference6
Versions
Meta has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Llama 2-13B | 18 Jul 2023 | 36.0 | #757 |
| LLaMA-13Bthis page | 24 Feb 2023 | – | – |
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Hard Prompts | 918#373 | Arena (LMArena) | |
| HellaSwagnot in index | 79.2%#29 | Epoch AI Benchmarking Hub | |
| BIG-Bench Hardnot in index | 37.9%#33 | Epoch AI Benchmarking Hub | |
| WinoGrandenot in index | 73.0%#37 | Epoch AI Benchmarking Hub | |
| ARC (AI2 Challenge)not in index | 52.7%#45 | Epoch AI Benchmarking Hub | |
| PIQAnot in index | 80.1%#33 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 883#368 | Arena (LMArena) |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Maths | 923#360 | Arena (LMArena) | |
| GSM8Knot in index | 20.6%#61 | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMLUnot in index | 47.7%#96 | Epoch AI Benchmarking Hub | |
| TriviaQAnot in index | 77.9%#20 | Epoch AI Benchmarking Hub | |
| OpenBookQAnot in index | 56.4%#22 | Epoch AI Benchmarking Hub | |
| LAMBADAnot in index | 75.2%#11 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Instruction Followingnot in index | 919#372 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 975#372 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 936#370 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 892#370 | Arena (LMArena) |
Multimodal
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| ScienceQAnot in index | 43.3%#21 | Epoch AI Benchmarking Hub |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 100.3#221 | Epoch AI Benchmarking Hub |
See also
Questions people ask
- Why does LLaMA-13B have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories; as of 25 Oct 2026 LLaMA-13B has 4 that count. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- When was LLaMA-13B released?
- Meta released LLaMA-13B on 24 Feb 2023.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “LLaMA-13B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/llama-13b.