Llama 3-70B
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
- Overall index39
- Reasoning34
- Coding41
- Agents & tools35
- Maths36
- Instruction following40
- Human preference42
- Long context23
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.
| Model | Released | Index | Rank |
|---|---|---|---|
| Llama 3.3 70B | 6 Dec 2024 | 39.9 | #521 |
| Llama 3.1 70B | 23 Jul 2024 | 40.8 | #507 |
| Llama 3-70Bthis page | 18 Apr 2024 | 38.7 | #542 |
| Llama 2-70B | 18 Jul 2023 | 33.5 | #583 |
| Llama 2 70B | – | – | – |
How its index has moved
8 Sep 2026 to 8 Nov 2026The 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 | Trend |
|---|---|---|---|
| GPQA Diamond | 40.6%#259 | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | 1280#284 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 37.9%#494 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 4.5%#512 | Artificial Analysis | |
| Kagi LLM Benchmark | 35.1%#118 | Kagi LLM Benchmark | |
| CritPtnot in index | 0.0%#329 | Artificial Analysis | |
| DTBenchnot in index | 54.2%#202 | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in index | 60.2%#72 | ForecastBench | |
| WinoGrandenot in index | 83.5%#9 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 1306#283 | Arena (LMArena) | |
| LiveCodeBench (AA)not in index | 19.8%#242 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Cybench | 5.0%#21 | Cybench | |
| Terminal-Bench Hard | 0.8%#354 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 0.0%#398 | Artificial Analysis |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| OTIS Mock AIME | 4.3%#260 | Epoch AI Benchmarking Hub | |
| MATH Level 5 | 22.6%#79 | Epoch AI Benchmarking Hub | |
| Arena Maths | 1259#271 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMLUnot in index | 79.3%#23 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 37.1%#298 | Artificial Analysis | |
| Arena Instruction Followingnot in index | 1259#283 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1277#282 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1254#271 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1274#274 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1254#297 | Arena (LMArena) |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR v1.1 | 0.0%#509 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 121.3#161 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2not in index | 5.5#590 | Artificial Analysis | |
| AA Progress Index v1not in index | 136.5#580 | Artificial Analysis |
Price history
The price above, per 1M tokens, every day it changed.
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.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0011 | – | 7.1 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0095 | – | 13.6 s |
| Code edit | 6,000 / 1,500 | $0.0080 | – | 33.1 s |
| Agentic coding session | 60,000 / 4,000 | $0.050 | – | 1.5 min |
| Structured extraction | 2,000 / 200 | $0.0019 | – | 4.9 s |
More from Meta
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.
[](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.