What are Llama 2-13B's benchmark scores?

As of 25 Oct 2026, Llama 2-13B scores 36.0 ±3.4 on the BenchLeader Index, strongest in composite (35) and weakest in coding (25). That rests on 5 independent benchmark results, and every score on this page links to its publisher.

How does Llama 2-13B rank?

Llama 2-13B is #757 of 785 ranked configurations on 25 Oct 2026. 139 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

When was Llama 2-13B released?

Meta released Llama 2-13B on 18 Jul 2023.

Meta Open weights: meta-llama/Llama-2-13b Compare with another model

Llama 2-13B

Llama 2-13B is a Meta open-weights model, released 18 Jul 2023. Its best configuration ranks #757 of 785 on the BenchLeader Index at 36.0 ±3.4, in the lower half. The ± is the point: 139 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in composite (35) and lowest in coding (25). Last measured 22 Oct 2026.

Blended price: –
Output speed: –
First answer: –
Context: 4k
Full answer: –
Cost per run: –
Released: 18 Jul 2023

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index36
Reasoning26
Coding25
Maths26
Human preference26
Composite35

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 2-13Bthis page	18 Jul 2023	36.0	#757
LLaMA-13B	24 Feb 2023	–	–

How its index has moved

19 Sept 2026 to 23 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

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
Arena Hard Prompts	1139#344	Arena (LMArena)
GPQA Diamond (AA)not in index	32.1%#512	Artificial Analysis
Humanity's Last Exam (AA)not in index	4.8%#475	Artificial Analysis
DTBenchnot in index	42.2%#228	Epoch AI Benchmarking Hub
HellaSwagnot in index	80.7%#26	Epoch AI Benchmarking Hub
BIG-Bench Hardnot in index	58.2%#18	Epoch AI Benchmarking Hub
WinoGrandenot in index	72.8%#41	Epoch AI Benchmarking Hub
ARC (AI2 Challenge)not in index	60.3%#35	Epoch AI Benchmarking Hub
PIQAnot in index	80.8%#28	Epoch AI Benchmarking Hub

Coding

Benchmark	not stated	Source	Trend
Arena Coding	1163#342	Arena (LMArena)

Maths

Benchmark	not stated	Source	Trend
Arena Maths	1110#335	Arena (LMArena)
GSM8Knot in index	36.9%#46	Epoch AI Benchmarking Hub

Knowledge

Benchmark	not stated	Source
MMLUnot in index	55.6%#87	Epoch AI Benchmarking Hub
TriviaQAnot in index	79.6%#17	Epoch AI Benchmarking Hub
OpenBookQAnot in index	57.0%#20	Epoch AI Benchmarking Hub
LAMBADAnot in index	76.5%#10	Epoch AI Benchmarking Hub

Instruction following

Benchmark	not stated	Source	Trend
Arena Instruction Followingnot in index	1110#344	Arena (LMArena)

Human preference

Benchmark	not stated	Source
Arena Text	1142#343	Arena (LMArena)
Arena Creative Writingnot in index	1092#348	Arena (LMArena)
Arena Multi-turnnot in index	1101#339	Arena (LMArena)
Arena Longer Queriesnot in index	1141#332	Arena (LMArena)

Multimodal

Benchmark	not stated	Source	Trend
ScienceQAnot in index	55.8%#20	Epoch AI Benchmarking Hub

Composite

Benchmark	not stated	Source	Trend
Epoch Capabilities Indexnot in index	105.6#212	Epoch AI Benchmarking Hub
AA Intelligence Index v4.3.2	5.3#586	Artificial Analysis

New this month

Questions people ask

What are Llama 2-13B's benchmark scores?: As of 25 Oct 2026, Llama 2-13B scores 36.0 ±3.4 on the BenchLeader Index, strongest in composite (35) and weakest in coding (25). That rests on 5 independent benchmark results, and every score on this page links to its publisher.
How does Llama 2-13B rank?: Llama 2-13B is #757 of 785 ranked configurations on 25 Oct 2026. 139 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was Llama 2-13B released?: Meta released Llama 2-13B on 18 Jul 2023.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Llama 2-13B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/llama-2-13b.