Scores by kind of claim
Each kind of claim is scored on its own, out of 100: the share that held up, with the range it likely falls in. Fewer resolved claims give a wider range.
-
Factual claims
Statements about the present or the past, checked against the record: did they hold up?
72 67 78 -
Predictions
Statements about events outside the person's control, checked once they fell due: did they come true?
Insufficient record: 1 prediction resolved, 5 needed for a score.
-
Promises
Commitments to the person's or organisation's own future action, with something to deliver: was it delivered?
Insufficient record: 4 promises resolved, 5 needed for a score.
-
Guidance
A company's own figures for its results over a period, checked against what it then reported.
Insufficient record: 1 guidance claim resolved, 5 needed for a score.
All types combined: 72 (likely 67 to 78, high confidence), from 101 claims: 101 factual claims. It mixes kinds of claim in different proportions for different people, so compare people kind by kind.
Jensen Huang's claims
11 claims
“overall performance is improved by 35 times, and a new level of inference performance previously unreachable by NVLink 72 is opened up.”
Jensen Huang, NVIDIA CEO, keynote 17 March 2026 Jensen Huang's GTC Speech (Full Text) (PANews)
Combining Groq with Vera Rubin under Dynamo scheduling improves overall performance by 35 times and reaches inference performance NVLink 72 could not previously reach.
Mostly false False in substance, right in a detail.
The second judge said mixed; the verdict shown is the first judge's.
Said for an organisation they lead or work for; it counts on both records.
What would count as true or false
Judged as of 2026-03-17. The claim has two parts: (a) Groq technology combined with Vera Rubin under Dynamo scheduling gives a 35x improvement in overall performance, on the metric NVIDIA states (e.g. throughput, tokens per second per user, or per-watt/per-MW output), against the baseline it states; and (b) this reaches an inference performance level an NVLink 72 system alone could not reach. NVIDIA technical materials published by that date (keynote slides, technical blog or whitepaper with stated methodology and baseline) count as evidence of what was measured. Independent benchmarks or analyses that contradict them take precedence. True: published results show about 35x (roughly 32x–38x) on the stated metric and baseline, plus an operating point beyond what NVL72 alone achieves. Mostly true: both parts hold but the multiple differs modestly (e.g. 30x or 40x), or it holds only for a narrower set of conditions than 'overall' implies, with that caveat stated in the source. Mixed: one part is supported and the other is not. Mostly false: the 35x figure comes from a single cherry-picked point (e.g. one latency regime) and is presented as overall, or the gain is real but much smaller than 35x. False: no such combined system or result existed as of the date, or evidence shows the gain is far below the claim (e.g. under 10x) or that NVL72 alone reaches the same performance.
Evidence
- Inside NVIDIA Groq 3 LPX: The Low-Latency Inference Accelerator for the NVIDIA Vera Rubin Platform | NVIDIA Technical Blog NVIDIA (developer.nvidia.com technical blog) · 16 March 2026 Own record
“the combination of Vera Rubin NVL72 and LPX delivers up to 35x higher TPS per megawatt at 400 TPS per user compared with the NVIDIA GB200 NVL72”
- Inside NVIDIA Groq 3 LPX: The Low-Latency Inference Accelerator for the NVIDIA Vera Rubin Platform | NVIDIA Technical Blog NVIDIA (developer.nvidia.com technical blog) · 16 March 2026 Own record
“In Figure 10, that premium tier is represented by a 2-trillion-parameter MoE model with a 400K input context window operating at roughly 400 TPS per user and beyond.”
- NVIDIA Spent $20 Billion Because GPUs Alone Can't Win the Inference Era | Barrack AI Barrack AI · 17 March 2026
“These figures are NVIDIA projections. No independent MLPerf results exist for Groq 3 LPU. They should be evaluated accordingly.”
- Nvidia's 35x inference number lost its denominator on the way to the headline Barista Labs · 16 March 2026
“Not 35x faster. Not 35x more tokens per second per chip. 35x more inference throughput per megawatt.”
Reasoning
NVIDIA's own technical blog (E1) gives the 35x figure as 'up to 35x higher TPS per megawatt at 400 TPS per user' against a GB200 NVL72 baseline. That is a peak result at one operating point and per-megawatt metric, not an overall performance improvement. Independent analyses (E4, E3) say the figure is a per-megawatt metric, not a general speed-up, and that it is an NVIDIA projection with no independent MLPerf results. E2 describes a premium tier at roughly 400 TPS per user, but nothing quoted shows that an NVL72 system alone could not reach that level.
Cite this claim
Jensen Huang, “Combining Groq with Vera Rubin under Dynamo scheduling improves overall performance by 35 times and reaches inference performance NVLink 72 could not previously reach.” (said 17 March 2026). Verdict: mostly false. Reliability API, claim c_240c42dde2d2, method 0.1.0+03d23c0e. https://epistacklabs.com/claims/c_240c42dde2d2
Claims without a verdict
Is a verdict here wrong, or do you speak for Jensen Huang? Reply on the claim's own page, with the form at its foot (how replies work). Verdicts are made automatically; how verdicts and scores are made.