BenchLeader

Llama 3.1 405B

Quality#252 of 339
41.8Index
Below the median
−8.4 on the median

As of 15 Nov 2026, Llama 3.1 405B by Meta scores 41.8 on the BenchLeader Index (608 ranked configurations), with its best results in human preference (49) and weakest in coding (35). Released 23 Jul 2024.

Key facts (as of 15 Nov 2026)

  • Llama 3.1 405B was released on 23 Jul 2024 (Meta).

In detail. Llama 3.1 405B is a Meta open-weights model, released 23 Jul 2024. Its best configuration ranks #507 of 608 on the BenchLeader Index at 41.8 ±3.7, in the lower half. The ± is the point: 188 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 human preference (49) and lowest in coding (35). Last measured 11 Nov 2026.

Blended price
–
Output speed
–
First answer
–
Context
128k
via Artificial Analysis
Cost per task
–
Tokens per task
–
Released
23 Jul 2024
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index42
  2. Reasoning36
  3. Coding35
  4. Agents & tools38
  5. Maths41
  6. Instruction following46
  7. Human preference49
  8. Long context36

Embed this rank

More badge styles
[![Llama 3.1 405B on BenchLeader: #246 overall](https://www.benchleader.com/badge/llama-3-1-405b.svg?style=compact)](https://www.benchleader.com/models/llama-3-1-405b)

Paste it at the top of README.md, beside your other badges. The badge redraws with every data update and links back to this page.

Get an email when Meta ships a new model

And once when it gets ranked, plus the weekly review on Mondays.

Choose providers and emails

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.

ModelReleasedIndexRank
Llama 3.1 405Bthis page23 Jul 202441.8#507
Llama 3 405B–––

How its index has moved

8 Sep 2026 to 15 Nov 2026
384348

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.

Metadata

Benchmarknot statedSourceTrend
AA Openness Indexnot in index38.9#155Artificial Analysis

Coding

Benchmarknot statedSourceTrend
WeirdML21.4%#144WeirdML
Arena Coding1376#225Arena (LMArena)
SWE-Bench Pro11.2%#22Scale AI SEAL
LiveCodeBench (AA)not in index30.5%#199Artificial Analysis

Agents & tools

Benchmarknot statedSourceTrend
Cybench7.5%#18Cybench
Terminal-Bench Hard6.8%#254Artificial Analysis
τ²-Bench Telecom (AA)not in index19.0%#348Artificial Analysis
TheAgentCompanynot in index7.4%#9TheAgentCompany

Knowledge

Benchmarknot statedSourceTrend
MMLU-Pro (HELM)not in index72.3%#35HELM Capabilities
MMLUnot in index84.5%#11Epoch AI Benchmarking Hub
TriviaQAnot in index82.7%#11Epoch AI Benchmarking Hub

Instruction following

Human preference

Benchmarknot statedSourceTrend
Arena Text1336#227Arena (LMArena)
EQ-Bench Creative Writing v3not in index868#110EQ-Bench
Arena Creative Writingnot in index1305#220Arena (LMArena)
Arena Multi-turnnot in index1340#213Arena (LMArena)
Arena Longer Queriesnot in index1329#238Arena (LMArena)

Long context

Benchmarknot statedSourceTrend
AA-LCR v1.125.3%#435Artificial Analysis

Composite

Safety & honesty

Benchmarknot statedSourceTrend
FORTRESSnot in index20.6%#41Scale AI SEAL
MASKnot in index61.4%#35Scale AI SEAL

More from Meta

New this month

See also

Embed or cite

Show where Llama 3.1 405B ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page.

[![Llama 3.1 405B on BenchLeader: #246 overall](https://www.benchleader.com/badge/llama-3-1-405b.svg)](https://www.benchleader.com/models/llama-3-1-405b)

Cite this

The ranking changes daily, so a reference carries the data date. APA style:

BenchLeader. (2026, November 15). Llama 3.1 405B on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 15, 2026, from https://www.benchleader.com/models/llama-3-1-405b

BibTeX:

@misc{benchleader_llama_3_1_405b_20261115,
  author       = {{BenchLeader}},
  title        = {{Llama 3.1 405B on the BenchLeader Index (method v1.4)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/llama-3-1-405b}},
  note         = {Data as of 2026-11-15}
}

Every badge style, the embeddable top-10 widget and how to cite the Index

Questions people ask

What are Llama 3.1 405B's benchmark scores?
As of 15 Nov 2026, Llama 3.1 405B scores 41.8 ±3.7 on the BenchLeader Index, strongest in human preference (49) and weakest in coding (35). That rests on independent benchmark results only, and every score on this page links to its publisher.
How does Llama 3.1 405B rank?
Llama 3.1 405B is #507 of 608 ranked configurations on 15 Nov 2026. 188 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 72.7.
When was Llama 3.1 405B released?
Meta released Llama 3.1 405B on 23 Jul 2024.

Data as of 15 Nov 2026. Compare with another model.

Cite as: BenchLeader, “Llama 3.1 405B: benchmarks, pricing, speed and rank”, data as of 15 Nov 2026, https://www.benchleader.com/models/llama-3-1-405b.