MetaLanguage model
Llama 3.1 405B Instruct
Llama 3.1 405B Instruct has no overall index value yet because there are too few independent benchmark results.
33out of 100same as last month
based on search, usage and attention
Summary
Llama 3.1 405B Instruct is the largest dense Instruct checkpoint in the Llama 3.1 family. The model card documents tool calling and open weights under the Llama 3.1 Community License.
Llama 3.1 70B Instruct and Llama 3.1 8B Instruct are the smaller dense tiers in the same family. The model card gives December 2023 as the knowledge cutoff for all three variants.
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 68 published benchmark results
Page 1 of 6
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
MMLU (CoT) (Show measurement, test conditions, and source)
- Source value
- 88.6
- Score
- 88.6
- Metric
- macro_avg/acc
- Unit
- %
- Benchmark version
- 0-shot CoT
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Llama 3.1 model card (commit e2e67cd)
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Llama 3.1 405B Instruct column in Meta's instruction-tuned table; 0 shots; metric macro_avg/acc.
- Context
- The card does not publish per-row sample counts, confidence intervals, or measurement dates.
ARC-C (Show measurement, test conditions, and source)
- Source value
- 96.9
- Score
- 96.9
- Metric
- acc
- Unit
- %
- Benchmark version
- 0-shot
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Llama 3.1 model card (commit e2e67cd)
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Llama 3.1 405B Instruct column in Meta's instruction-tuned table; 0 shots; metric acc.
- Context
- The card does not publish per-row sample counts, confidence intervals, or measurement dates.
MultiPL-E HumanEval (Show measurement, test conditions, and source)
- Source value
- 75.2
- Score
- 75.2
- Metric
- pass@1
- Unit
- %
- Benchmark version
- 0-shot
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Llama 3.1 model card (commit e2e67cd)
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Llama 3.1 405B Instruct column in Meta's instruction-tuned table; 0 shots; metric pass@1.
- Context
- The card does not publish per-row sample counts, confidence intervals, or measurement dates.
MultiPL-E MBPP (Show measurement, test conditions, and source)
- Source value
- 65.7
- Score
- 65.7
- Metric
- pass@1
- Unit
- %
- Benchmark version
- 0-shot
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Llama 3.1 model card (commit e2e67cd)
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Llama 3.1 405B Instruct column in Meta's instruction-tuned table; 0 shots; metric pass@1.
- Context
- The card does not publish per-row sample counts, confidence intervals, or measurement dates.
MATH (CoT) (Show measurement, test conditions, and source)
- Source value
- 73.8
- Score
- 73.8
- Metric
- final_em
- Unit
- %
- Benchmark version
- 0-shot CoT
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Llama 3.1 model card (commit e2e67cd)
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Llama 3.1 405B Instruct column in Meta's instruction-tuned table; 0 shots; metric final_em.
- Context
- The card does not publish per-row sample counts, confidence intervals, or measurement dates.
API-Bank (Show measurement, test conditions, and source)
- Source value
- 92
- Score
- 92
- Metric
- acc
- Unit
- %
- Benchmark version
- 0-shot
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Llama 3.1 model card (commit e2e67cd)
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Llama 3.1 405B Instruct column in Meta's instruction-tuned table; 0 shots; metric acc.
- Context
- The card does not publish per-row sample counts, confidence intervals, or measurement dates.
BFCL (Show measurement, test conditions, and source)
- Source value
- 88.5
- Score
- 88.5
- Metric
- acc
- Unit
- %
- Benchmark version
- 0-shot
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Llama 3.1 model card (commit e2e67cd)
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Llama 3.1 405B Instruct column in Meta's instruction-tuned table; 0 shots; metric acc.
- Context
- The card does not publish per-row sample counts, confidence intervals, or measurement dates.
Gorilla Benchmark API Bench (Show measurement, test conditions, and source)
- Source value
- 35.3
- Score
- 35.3
- Metric
- acc
- Unit
- %
- Benchmark version
- 0-shot
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Llama 3.1 model card (commit e2e67cd)
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Llama 3.1 405B Instruct column in Meta's instruction-tuned table; 0 shots; metric acc.
- Context
- The card does not publish per-row sample counts, confidence intervals, or measurement dates.
Nexus (0-shot) (Show measurement, test conditions, and source)
- Source value
- 58.7
- Score
- 58.7
- Metric
- macro_avg/acc
- Unit
- %
- Benchmark version
- 0-shot
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Llama 3.1 model card (commit e2e67cd)
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Llama 3.1 405B Instruct column in Meta's instruction-tuned table; 0 shots; metric macro_avg/acc.
- Context
- The card does not publish per-row sample counts, confidence intervals, or measurement dates.
Multilingual MGSM (CoT) (Show measurement, test conditions, and source)
- Source value
- 91.6
- Score
- 91.6
- Metric
- em
- Unit
- %
- Benchmark version
- 0-shot CoT
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Llama 3.1 model card (commit e2e67cd)
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Llama 3.1 405B Instruct column in Meta's instruction-tuned table; 0 shots; metric em.
- Context
- The card does not publish per-row sample counts, confidence intervals, or measurement dates.
Multilingual MMLU (Portuguese) (Show measurement, test conditions, and source)
- Source value
- 84.95
- Score
- 84.95
- Metric
- macro_avg/acc
- Unit
- %
- Benchmark version
- 5-shot
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Llama 3.1 model card (commit e2e67cd)
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Llama 3.1 405B Instruct column in Meta's instruction-tuned multilingual table; MMLU, 5-shot, macro_avg/acc.
- Context
- The card does not publish per-row sample counts, confidence intervals, or measurement dates.
Multilingual MMLU (Spanish) (Show measurement, test conditions, and source)
- Source value
- 85.08
- Score
- 85.08
- Metric
- macro_avg/acc
- Unit
- %
- Benchmark version
- 5-shot
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Llama 3.1 model card (commit e2e67cd)
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Llama 3.1 405B Instruct column in Meta's instruction-tuned multilingual table; MMLU, 5-shot, macro_avg/acc.
- Context
- The card does not publish per-row sample counts, confidence intervals, or measurement dates.
Page 1 of 6
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
The 100 most popular models of this category, 0 to 100, higher is more popular
20 of 101 models
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 7, 2026
Llama 3.1 405B InstructAREX-2 33Command A Plus 33Nex-N2-mini 33Llama 3.3 Nemotron Super 49B v1 33
Method changes in the timeline, a jump at these points is no market event:
- 1November 1, 2026: Value only with search or usage data, 30-day attention
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
Similar models
More models of the same kind as Llama 3.1 405B Instruct, chosen by model line, developer, size, price and release date.
- Llama 4 MaverickMeta · same developer
- Llama 4 Maverick 17B InstructMeta · same developer
- Llama 3.1 70B InstructMeta · same developer
- Llama 3.1 70BMeta · same developer
- Code Llama 70B InstructMeta · same developer
- Llama 3.1 8B InstructMeta · same developer
- Llama-3.2-1BMeta · same developer
- Llama 3.1 8BMeta · same developer
All specifications
Architecture
Input and output
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
Frequently asked questions about Llama 3.1 405B Instruct
What is the knowledge cutoff of Llama 3.1 405B Instruct?
December 2023, according to Meta. That is 7 months before release.
Stated by Meta
How large is the context window of Llama 3.1 405B Instruct?
131,072 tokens. That is how much text Llama 3.1 405B Instruct reads at once, about 200 A4 pages.
Page count as a rule of thumb from Artificial Analysis
Can I run Llama 3.1 405B Instruct locally?
Yes, the weights are open. With 405B parameters it needs a lot of memory, more a server than a laptop.
Stated by Meta
- Open weights
- yes
- License
- Llama 3.1 Community
- Parameters
- 405B
- active per token
- n/a
Sources and data date
Show all 24 sources
Benchmark sources at a glance
Which independent evaluators tested this model. This is coverage, not a quality ranking.
| Evaluator | Test series | Composite indices | Recorded active measurements |
|---|---|---|---|
| Scale AI Evals | 0 | 0 | 1 |
Without vendor claims and historical or disputed results; those stay labelled in the single values. 1 measurements are not yet assigned to a test series.