Meta·#380 of 504 in the all-versions archive
Llama 3.1 70B Instruct is a language model from Meta. It ranks #380 of 504 in ModelCap's all-versions archive, with an Index score of 25.3, measured on 2 public benchmarks. Its score range of 20.4–30.2 spans positions #354–#415. It is listed at $0.72 per million input tokens and $0.72 per million output tokens from one provider. It reads up to 131K tokens of context, and its weights are downloadable after an access request.
Figures as of 6 Nov 2026, 20:32 UTC · download the public dataset · methodology
Superseded by Llama 3.3 70B Instruct. It no longer holds a current-board position; its all-versions archive rank is #380.
Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. They remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.
Showing 20 of 40 rows.
BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.
These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.
The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.
Not yet published: a link to the licence terms, pinned evaluation dataset versions.
A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.
Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.
OpenRouter weekly popularity across the full model catalogue.
Independent providers versus the model's open or closed cohort, weighted by uptime.
Hugging Face 30-day downloads for open models; neutral for closed models.
Time since first public availability, on a six-month half-life.
meta-llama/llama-3.1-70b-instructOpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. OpenRouter metadata
Gated access. The weights are hosted behind an access request or acceptance step. Review the publisher's access requirements and license before use or redistribution.
Llama 3.1 70B Instruct is a superseded version and is not on the current board as of 6 November 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.
Llama 3.1 70B Instruct is listed at $0.72 per 1M input tokens and $0.72 per 1M output tokens as of 6 November 2026. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $1.80 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.
Llama 3.1 70B Instruct has a published context window of 131K tokens (131,072). The snapshot lists a 8,192 token catalogue-declared route output cap. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. The providers table lists each endpoint's context limit.
Gated access (llama3.1). The weights are hosted behind an access request or acceptance step. Review the publisher's access requirements and license before use or redistribution. The repository is meta-llama/Meta-Llama-3.1-70B-Instruct on Hugging Face.
One provider serves Llama 3.1 70B Instruct through OpenRouter as of 6 November 2026: Amazon Bedrock. Each provider's price, context limit, quantization and measured uptime are in the providers table above.
Llama 3.1 70B Instruct has published results on 2 public boards tracked by ModelCap as of 6 November 2026: Arena text 1293 (#292 of 419) and Arena coding 1333 (#289 of 414). Each board page ranks every tracked model on that benchmark. The ModelCap Index scores the results its methodology admits, with published uncertainty, and shows reference boards without scoring them.
Llama 3.1 70B Instruct first appeared in the catalogue on 23 Jul 2024, with a published knowledge cutoff of 2023-12-31. It has since been superseded by Llama 3.3 70B Instruct. Rank and price movements since then are recorded on the site's changes feed.