none reviewed yet · 2 benchmark observations · latest capture Sep 11, 2026
Inspect the evidenceMeta · MODEL PROFILE
Llama 3.3 70B Instruct
Catalogue discovery; compare availability, context, and public token pricing before benchmark review.
No editorial score yet — missing data is not a low score
How scoring worksVerified rates (Sep 11, 2026) · 100 runs / month at your token settings
Adjust workloadAt a glance
9 facts- Provider
- Meta
- Type
- API model
- Access
- OpenRouter API
- Context
- 131,072 tokens
- Maximum output
- 16,384 tokens
- License / weights
- Open weights
- Input modalities
- text
- Output modalities
- text
- Pricing notes
- $0.1 input / $0.32 output per 1M tokens on OpenRouter.
The practical trade-offs
Documented strengths
- Current model catalogue entry with a public API identifier and pricing metadata.
Limitations to check
- No normalized frontend-quality score has been assigned.
- Popularity and recency are not treated as quality evidence.
Follow the source
2 source linksEvidence & conditions
2Source links
NoneReviewed records
2Benchmark runs
Sep 11, 2026Latest capture
- Evidence source 1
openrouter.aiDate not recorded - Evidence source 2
openrouter.aiDate not recorded
Benchmark observations
HumanEval Inspect conditions
- name
- HumanEval
- value
- 88.4
- unit
- %
- source Url
- https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
- checked At
- 2026-09-08T19:31:52Z
- attribution
- provider-reported
- configuration
- Llama 3.3 70B Instruct; zero-shot; pass@1.
MBPP EvalPlus (base) Inspect conditions
- name
- MBPP EvalPlus (base)
- value
- 87.6
- unit
- %
- source Url
- https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
- checked At
- 2026-09-08T19:31:52Z
- attribution
- provider-reported
- configuration
- Llama 3.3 70B Instruct; zero-shot; pass@1; base evaluation subset.
Source reports, measured results, and editorial assessments are separate evidence types. Source dates do not imply a new benchmark run. Capture dates are shown when recorded; otherwise we say the capture date was not recorded. Recorded dates are compared with this catalogue snapshot (Sep 11, 2026), not today’s date.
Method AIS-V2
How this page is assessed
Quality claims follow Method AIS-V2.
Money never buys rank — commercial relationships cannot change rank, eligibility, evidence quality, or publication timing.
Submit or claim a listing is free and does not skip the editorial queue.
Private · this device only