Meta model product
Llama 3.1 70B
1 70B is a large language model optimized for multilingual dialogue use cases.
Updated Oct 23, 2026. Default version: Llama 3.1 70B Instruct
LLMBoard Score10.5Llama 3.1 70B Instruct
Coverage20%16 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable
Llama 3.1 70B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Llama 3.1 70B Benchmark Results
Benchmark scores for Llama 3.1 70B Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkGSM-8K (CoT) | Score95.10% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMATH (CoT) | Score68.00% | Rank01 | Participants6 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMBPP ++ base version | Score86.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkAPI-Bank | Score90.00% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkBFCL | Score84.80% | Rank02 | Participants11 | Percentile90.00% | EvidenceC | Evaluated |
| BenchmarkGorilla Benchmark API Bench | Score29.70% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkMMLU (CoT) | Score86.00% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkMultilingual MGSM (CoT) | Score86.90% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkMultipl-E HumanEval | Score65.50% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkMultipl-E MBPP | Score62.00% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkNexus | Score56.70% | Rank02 | Participants4 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score94.80% | Rank04 | Participants35 | Percentile91.18% | EvidenceC | Evaluated |
| BenchmarkDROP | Score79.60% | Rank14 | Participants30 | Percentile55.17% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score87.50% | Rank34 | Participants70 | Percentile52.17% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score80.50% | Rank45 | Participants66 | Percentile32.31% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score83.60% | Rank49 | Participants103 | Percentile52.94% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score66.40% | Rank109 | Participants142 | Percentile23.40% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,260.93 rating | Rank192 | Participants218 | Percentile11.98% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,293.41 rating | Rank192 | Participants218 | Percentile11.98% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score41.70% | Rank223 | Participants256 | Percentile12.94% | EvidenceC | Evaluated |
Llama 3.1 70B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryfrench | Rank168 | Rating / score1,261.52 | Votes501 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank171 | Rating / score1,140.34 | Votes873 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank171 | Rating / score1,301.81 | Votes501 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank172 | Rating / score1,221.74 | Votes1,353 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank172 | Rating / score1,132.45 | Votes1,428 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank172 | Rating / score1,253.05 | Votes606 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank174 | Rating / score1,174.94 | Votes1,428 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank174 | Rating / score1,287.99 | Votes606 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank175 | Rating / score1,187.15 | Votes873 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank176 | Rating / score1,256.21 | Votes1,353 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank179 | Rating / score1,328.46 | Votes3,177 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank180 | Rating / score1,283.39 | Votes3,177 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank184 | Rating / score1,276.00 | Votes9,381 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank184 | Rating / score1,257.17 | Votes2,821 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank185 | Rating / score1,251.66 | Votes7,677 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank186 | Rating / score1,293.66 | Votes29,694 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank186 | Rating / score1,318.64 | Votes9,381 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank187 | Rating / score1,321.16 | Votes29,694 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank188 | Rating / score1,235.06 | Votes6,381 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank188 | Rating / score1,313.32 | Votes2,821 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank189 | Rating / score1,229.78 | Votes8,719 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank189 | Rating / score1,253.49 | Votes6,524 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank190 | Rating / score1,333.10 | Votes9,389 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank190 | Rating / score1,269.04 | Votes7,677 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank190 | Rating / score1,288.68 | Votes10,405 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank191 | Rating / score1,263.74 | Votes8,719 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank191 | Rating / score1,274.91 | Votes6,524 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank192 | Rating / score1,176.60 | Votes34,840 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank192 | Rating / score1,256.15 | Votes10,405 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank192 | Rating / score1,260.93 | Votes55,240 | ObservationsN/A | Result date |
Llama 3.1 70B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.40 input, $0.40 output per 1M via OpenRouter
- Tracked offerings
- 6
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOpenRouter | Provider model IDmeta-llama/llama-3.1-70b-instruct | Regionglobal | Input / 1M$0.40 | Output / 1M$0.40 | Context131.1K | Updated |
| ProviderKilo Gateway | Provider model IDmeta-llama/llama-3.1-70b-instruct | Regionglobal | Input / 1M$0.40 | Output / 1M$0.40 | Context131.1K | Updated |
| ProviderAmazon Bedrock | Provider model IDmeta.llama3-1-70b-instruct-v1:0 | Regionglobal | Input / 1M$0.72 | Output / 1M$0.72 | Context128K | Updated |
| ProviderVercel AI Gateway | Provider model IDmeta/llama-3.1-70b | Regionglobal | Input / 1M$0.72 | Output / 1M$0.72 | Context128K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDllama-3.1-70b-instruct | Regionglobal | Input / 1M$0.72 | Output / 1M$0.72 | Context128K | Updated |
| ProviderMerge Gateway | Provider model IDmeta/llama-3.1-70b-instruct | Regionglobal | Input / 1M$0.99 | Output / 1M$0.99 | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Llama 3.1 70B Runtime Performance
Provider-specific output speed and catalog latency for Llama 3.1 70B Instruct. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderCerebras | Output Speed1,204.00 tok/s | Catalog Latency0.20 s | Max Input128K | Max Output128K | Updated |
| ProviderGroq | Output Speed250.00 tok/s | Catalog Latency0.50 s | Max Input128K | Max Output128K | Updated |
| ProviderSambanova | Output Speed74.00 tok/s | Catalog Latency0.50 s | Max Input128K | Max Output128K | Updated |
| ProviderDeepInfra | Output Speed25.00 tok/s | Catalog Latency0.50 s | Max Input128K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Llama 3.1 70B Specifications
Technical details for the model's default version.
- Version
- Llama 3.1 70B Instruct
- Released
- Jul 23, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 70B
- Context window
- 131.1K
- Max output
- 128K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Llama 3.1 Community License
Llama 3.1 70B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionLlama 3.1 70B Instruct | Released | LLMBoard10.51 | Parameters70B | Context131.1K | Max output128K | Open weightsYes | LicenseLlama 3.1 Community License |
Models similar to Llama 3.1 70B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ME
Llama 4 Scout
Meta
ME
Llama 3.2 90B
Meta
ME
Llama 3.3 70B
Meta
ME
Llama 3.1 8B
Meta
ME
Llama 3.2 11B
Meta
ME
Llama 3.2 3B
Meta
What is Llama 3.1 70B?
Key information about Llama 3.1 70B and its available data.
1 70B Instruct is a large language model from Meta optimized for multilingual dialogue use cases. It outperforms many available open source and closed chat models on common industry benchmarks.
Data as of 2026-10-22.
FAQ
Common questions about Llama 3.1 70B.
When was Llama 3.1 70B released?
Llama 3.1 70B's default version was released on Jul 23, 2024.
How much does Llama 3.1 70B cost?
No official standard PAYG price is currently available for Llama 3.1 70B. The lowest tracked third-party offer starts at $0.40 input and $0.40 output via OpenRouter.
Who created Llama 3.1 70B?
Llama 3.1 70B was created by Meta.
What is the context window for Llama 3.1 70B?
The default version has a 131.1K token context window.
Is Llama 3.1 70B open weight?
Yes. The default version is marked as open weight under Llama 3.1 Community License.
How many API providers offer Llama 3.1 70B?
6 provider offerings are linked to the default version.