Indicators / series
aa.llama_3_1_nemotron_instruct_70b.output_tokens_per_second.pt
Source: Artificial Analysis API (Intelligence Index, blended price, speed) (Artificial Analysis) · Artificial Analysis API terms; attribution required · CSV
Artificial Analysis
| id | value | grade | as of date | published date | tier | audited vs reported | extraction method | review status | retrieved at | http status | content hash | supersedes id | url | flags |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 49ca1cb39df2dd08 | 63.3 tokens per second | grade B, evidence tier 3 | 2026-09-11 | 2026-09-11 | 3 | reported | api | approved | 2026-09-11 00:55 | 200 | 7d26b4817132 | — | source page | |
| 01bb6410a7785402 | 60.5 tokens per second | grade B, evidence tier 3 | 2026-09-12 | 2026-09-12 | 3 | reported | api | approved | 2026-09-12 07:40 | 200 | 71ec2312175f | — | source page | |
| 02ee927d7b12b1d0 | 62.3 tokens per second | grade B, evidence tier 3 | 2026-09-13 | 2026-09-13 | 3 | reported | api | approved | 2026-09-13 11:59 | 200 | 61104c5aa480 | — | source page | |
| 419482e0a94ce75e | 115 tokens per second | grade B, evidence tier 3 | 2026-09-14 | 2026-09-14 | 3 | reported | api | approved | 2026-09-14 12:59 | 200 | c318f17ae2a2 | — | source page | |
| f9add7b018009d97 | 114 tokens per second | grade B, evidence tier 3 | 2026-09-15 | 2026-09-15 | 3 | reported | api | approved | 2026-09-15 11:52 | 200 | bf62a8ea70e6 | — | source page | |
| 925647dc1eeeffd8 | 162 tokens per second | grade B, evidence tier 3 | 2026-09-21 | 2026-09-21 | 3 | reported | api | approved | 2026-09-21 04:47 | 200 | 54c96114bc6d | — | source page | |
| ec43239ef5e6c265 | 154 tokens per second | grade B, evidence tier 3 | 2026-09-22 | 2026-09-22 | 3 | reported | api | approved | 2026-09-22 11:48 | 200 | 1e2f98aa6450 | — | source page | |
| 13f02ad0f59cc4a8 | 42.5 tokens per second | grade B, evidence tier 3 | 2026-09-23 | 2026-09-23 | 3 | reported | api | approved | 2026-09-23 11:47 | 200 | 907e4d2fbaea | — | source page |
Raw snippets and dispute text
- 49ca1cb39df2dd08 llama-3-1-nemotron-instruct-70b (nvidia) median_output_tokens_per_second 63.28
- 01bb6410a7785402 llama-3-1-nemotron-instruct-70b (nvidia) median_output_tokens_per_second 60.519
- 02ee927d7b12b1d0 llama-3-1-nemotron-instruct-70b (nvidia) median_output_tokens_per_second 62.319
- 419482e0a94ce75e llama-3-1-nemotron-instruct-70b (nvidia) median_output_tokens_per_second 114.594
- f9add7b018009d97 llama-3-1-nemotron-instruct-70b (nvidia) median_output_tokens_per_second 113.918
- 925647dc1eeeffd8 llama-3-1-nemotron-instruct-70b (nvidia) median_output_tokens_per_second 162.47
- ec43239ef5e6c265 llama-3-1-nemotron-instruct-70b (nvidia) median_output_tokens_per_second 154.419
- 13f02ad0f59cc4a8 llama-3-1-nemotron-instruct-70b (nvidia) median_output_tokens_per_second 42.54