BenchLeader

Llama 3-70B

Quality#284 of 333
38.7Index
Bottom quarter
−11.3 on the median
Price#144 of 249
$1.18per 1M tokens
Dearer than most
1.4× the median
Speed#172 of 215
46tokens/s
Bottom quarter
0.6× the median

119 cheaper ranked models score higher: DeepSeek V4.1 Flash 1017 (59.2, $0.525), Qwen3.6 Plus (59.1, $1.13), DeepSeek V4.1 Flash (59.0, $0.518) and 116 more.

As of 8 Nov 2026, Llama 3-70B by Meta scores 38.7 on the BenchLeader Index (593 ranked configurations), with its best results in human preference (42) and weakest in long context (23). API pricing: $0.650 per 1M input tokens and $2.75 per 1M output tokens ($1.18 blended at 3:1), list price on 8 Nov 2026. It streams about 46 tokens/s (Artificial Analysis). Released 18 Apr 2024.

Key facts (as of 8 Nov 2026)

  • Llama 3-70B API pricing: $0.650 per 1M input tokens and $2.75 per 1M output tokens ($1.18 blended at 3:1) (list price, 8 Nov 2026).
  • Llama 3-70B streams about 46 tokens/s (Artificial Analysis, 8 Nov 2026).
  • Llama 3-70B was released on 18 Apr 2024 (Meta).

In detail. Llama 3-70B is a Meta open-weights model, released 18 Apr 2024. Its best configuration ranks #542 of 593 on the BenchLeader Index at 38.7 ±3.5, in the lower half. The ± is the point: 140 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 (42) and lowest in long context (23). At $1.18 per million tokens blended it is mid-priced. Output speed of 46 tokens per second puts it in the slowest quarter, with a first answer in 0.6 s. Last measured 6 Nov 2026.

Blended price
$1.18/M
$0.650 in · $2.75 out
via Artificial Analysis
Output speed
46 tok/s
measured by Artificial Analysis
First answer
0.55 s
first token 0.55 s
Context
8k
via Artificial Analysis
Full answer
–
Cost per task
–
Tokens per task
–
Released
18 Apr 2024
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index39
  2. Reasoning34
  3. Coding41
  4. Agents & tools35
  5. Maths36
  6. Instruction following40
  7. Human preference42
  8. Long context23

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 5 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 3.3 70B6 Dec 202439.9#521
Llama 3.1 70B23 Jul 202440.8#507
Llama 3-70Bthis page18 Apr 202438.7#542
Llama 2-70B18 Jul 202333.5#583
Llama 2 70B–––

How its index has moved

8 Sep 2026 to 8 Nov 2026
354044

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.

Coding

Benchmarknot statedSourceTrend
Arena Coding1306#283Arena (LMArena)
LiveCodeBench (AA)not in index19.8%#242Artificial Analysis

Agents & tools

Benchmarknot statedSourceTrend
Cybench5.0%#21Cybench
Terminal-Bench Hard0.8%#354Artificial Analysis
τ²-Bench Telecom (AA)not in index0.0%#398Artificial Analysis

Knowledge

Benchmarknot statedSourceTrend
MMLUnot in index79.3%#23Epoch AI Benchmarking Hub

Instruction following

Benchmarknot statedSourceTrend
IFBench37.1%#298Artificial Analysis
Arena Instruction Followingnot in index1259#283Arena (LMArena)

Human preference

Benchmarknot statedSourceTrend
Arena Text1277#282Arena (LMArena)
Arena Creative Writingnot in index1254#271Arena (LMArena)
Arena Multi-turnnot in index1274#274Arena (LMArena)
Arena Longer Queriesnot in index1254#297Arena (LMArena)

Long context

Benchmarknot statedSourceTrend
AA-LCR v1.10.0%#509Artificial Analysis

Composite

Benchmarknot statedSourceTrend
Epoch Capabilities Indexnot in index121.3#161Epoch AI Benchmarking Hub
AA Intelligence Index v4.3.2not in index5.5#590Artificial Analysis
AA Progress Index v1not in index136.5#580Artificial Analysis

Price history

The price above, per 1M tokens, every day it changed.

$0.00$0.756$1.51$2.27$3.03Sep 26Oct 26Nov 26
input outputnow $0.650 in · $2.75 out

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0011–7.1 s
Summarize a 30-page report12,000 / 600$0.0095–13.6 s
Code edit6,000 / 1,500$0.0080–33.1 s
Agentic coding session60,000 / 4,000$0.050–1.5 min
Structured extraction2,000 / 200$0.0019–4.9 s

More from Meta

New this month

See also

Embed or cite

Show where Llama 3-70B 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. To see ranks like this on OpenRouter and Hugging Face model pages, get the Chrome extension.

[![Llama 3-70B on BenchLeader: #277 overall](https://www.benchleader.com/badge/llama-3-70b.svg)](https://www.benchleader.com/models/llama-3-70b)

Cite this

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

BenchLeader. (2026, November 8). Llama 3-70B on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 8, 2026, from https://www.benchleader.com/models/llama-3-70b

BibTeX:

@misc{benchleader_llama_3_70b_20261108,
  author       = {{BenchLeader}},
  title        = {{Llama 3-70B on the BenchLeader Index (method v1.4)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/llama-3-70b}},
  note         = {Data as of 2026-11-08}
}

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

Questions people ask

What are Llama 3-70B's benchmark scores?
As of 8 Nov 2026, Llama 3-70B scores 38.7 ±3.5 on the BenchLeader Index, strongest in human preference (42) and weakest in long context (23). That rests on independent benchmark results only, and every score on this page links to its publisher.
How does Llama 3-70B rank?
Llama 3-70B is #542 of 593 ranked configurations on 8 Nov 2026. 140 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 69.4.
How much does Llama 3-70B cost per 1M tokens?
As of 8 Nov 2026, Llama 3-70B costs $0.650 per 1M input tokens and $2.75 per 1M output tokens, $1.18 blended (three input tokens per output token). The list price last changed on 9 Sep 2026.
When was Llama 3-70B released?
Meta released Llama 3-70B on 18 Apr 2024.

Data as of 8 Nov 2026. Compare with another model.

Cite as: BenchLeader, “Llama 3-70B: benchmarks, pricing, speed and rank”, data as of 8 Nov 2026, https://www.benchleader.com/models/llama-3-70b.