I conducted a 3 scale experiment for science. Claude Opus suggested the least expensive model until he saw the results. Now he says spend for Withings
I loaded all the stats from the 3 scales
Renpho Smart Scale
Wyze Ultra
Withings Body Scan (@ageless64 I’m still intrigued their less expensive models after seeing your results and how wildly off the trunk is on their body scan… perhaps measuring my arms is not worth the price difference).
I thought it was worth mentioning all 3 are very inaccurate on visceral fat, so if you use one and don’t get a dexa, be kind to yourself!
My dexa visceral is .79, Wyze is 4.0, Withings is 1.9, Renpho is 3.0
Opus said:
This is excellent data — well-structured comparisons across multiple days with DEXA as ground truth. Let me break this down systematically by what matters most for your sarcopenia-prevention goal.
MUSCLE Accuracy vs. DEXA (the metric that matters most for you)
LEGS (your primary target):
| Scale |
Apr 2 |
Apr 4 |
Avg Offset |
Day-to-Day Variance |
| Withings |
+1.1 |
+1.2 |
+1.15 lb |
0.3 lb |
| Wyze |
+1.2 |
+1.0 |
+1.1 lb |
0.2 lb |
| Renpho |
+3.2 |
+3.2 |
+3.2 lb |
0.0 lb |
All three scales overestimate leg muscle vs. DEXA, but Renpho is off by a huge margin — over 3 lbs on a 23.2 lb compartment. That’s a ~14% overestimate. For sarcopenia tracking, that’s dangerous because it would mask real losses. If you lost 2 lbs of leg muscle over the next year, Renpho would still show you above your current DEXA value. You’d feel reassured while actually declining.
Withings and Wyze are both around +1.1 lb offset, which is a ~5% systematic bias — tolerable as long as it’s consistent over time, because you’d track the delta, not the absolute number.
TRUNK:
This is where the scales diverge most dramatically.
- Withings: +8.7 to +9.4 lb (red — wildly high, ~25% overestimate)
- Wyze: -2.6 to -3.0 lb (red — underestimates)
- Renpho: -0.1 to -0.3 lb (green — nearly perfect)
Renpho nails trunk muscle. Withings is absurdly high here. But trunk muscle isn’t your sarcopenia priority, so while this is interesting, it shouldn’t drive the decision.
ARMS:
- Withings: +0.1 to +0.3 lb (green — excellent)
- Wyze: -0.4 to -0.6 lb (orange — slight underestimate)
- Renpho: +0.2 to 0.0 lb (green — excellent)
Arms are small compartments where all three are reasonably close, but Wyze consistently underestimates here.
FAT Accuracy vs. DEXA
LEGS (primary target):
- Withings: -0.6 to -0.5 lb (good)
- Wyze: -3.5 to -3.1 lb (terrible — underestimates leg fat by ~30%)
- Renpho: -4.7 to -3.9 lb (even worse)
This is the flip side of the muscle story. Wyze and Renpho are dramatically underreporting leg fat. Since BIA can’t truly see inside each limb independently, what’s happening is that Wyze and Renpho are misclassifying leg fat as leg muscle — which is exactly why their leg muscle numbers are inflated. Renpho does this the worst, which explains both its +3.2 lb muscle overestimate and its -4.7 lb fat underestimate in legs. The errors are almost perfectly mirrored.
Withings, by contrast, gets leg fat within 0.5–0.6 lb of DEXA, meaning its tissue partitioning algorithm in the lower extremities is substantially more accurate.
TRUNK FAT:
- Withings: -3.0 to -3.1 lb (underestimates)
- Wyze: -1.5 to 0.0 lb (decent, and improving on day 2)
- Renpho: +0.4 to +1.8 lb (variable)
Here Withings underestimates trunk fat, which is the mirror of its trunk muscle overestimate. The scale appears to be shifting tissue from fat → muscle in the trunk compartment. This is a known BIA limitation with 4-electrode scales.
Day-to-Day Consistency (Critical for Trend Tracking)
This is arguably more important than absolute accuracy for your use case. You need to detect a 1–2 lb change in leg muscle over 6–12 months. If the scale’s noise is 1 lb day-to-day, that change disappears into the noise floor.
Withings (3-day variance):
- Leg muscle: 0.3 lb
- Leg fat: 0.4 lb
- Trunk muscle: 1.1 lb (noisier, but not your target)
- Arms: 0.2 lb muscle, 0.0 lb fat
Wyze (3-day variance):
- Leg muscle: 0.2 lb
- Leg fat: 0.4 lb
- Trunk muscle: 0.4 lb
- Arms: 0.2 lb muscle, 0.4 lb fat
Renpho (2-day variance):
- Leg muscle: 0.0 lb (only 2 data points though)
- Trunk muscle: 0.4 lb
- Arms: 0.2 lb
Both Withings and Wyze show tight day-to-day consistency in legs, which is good. We only have 2 Renpho data points so its consistency is harder to judge, but the numbers were stable.
The Bottom Line
For sarcopenia tracking specifically — legs are what matter, and here’s the hierarchy:
Withings is the clear winner. Here’s why:
-
Tissue partitioning accuracy in legs is far superior. Withings gets leg muscle within +1.1 lb AND leg fat within -0.6 lb. The errors are small and don’t mirror each other in a way that suggests gross misclassification. Wyze and especially Renpho are systematically misclassifying leg fat as leg muscle — their muscle numbers look better than they are, and their fat numbers are implausibly low.
-
Day-to-day consistency is tight where it counts. Leg muscle variance of 0.3 lb means a real 1.5 lb change over 6 months would be clearly detectable above noise. That’s the signal resolution you need.
-
The trunk muscle overestimate is a known, stable bias. Yes, Withings adds ~9 lbs to trunk muscle — but it does this consistently every day. Since you’re not tracking trunk muscle for sarcopenia decisions, this is irrelevant. And if it stays consistently wrong by the same amount, it wouldn’t corrupt trend data even if you did care about trunk.
Wyze is a reasonable second choice — good leg muscle consistency (0.2 lb variance) and similar offset to Withings (+1.1 lb). But its leg fat underestimate of 3+ lbs reveals that its tissue partitioning algorithm is doing something fundamentally wrong in the lower extremities. Over time, if that misclassification drifts, your muscle trend data becomes unreliable.
Renpho is the wrong tool for this job. The +3.2 lb leg muscle overestimate paired with the -4.7 lb leg fat underestimate tells you the algorithm is essentially guessing at limb composition. It nails trunk beautifully, but for your specific goal — detecting early leg muscle loss — it would give you false reassurance.
My Recommendation
Invest in the Withings for long-term leg muscle tracking. Use it under the same conditions every time (morning, fasted, same hydration routine), and track 7-day rolling averages rather than individual readings to further smooth the 0.3 lb noise. Cross-reference with DEXA every 6 months at BodySpec to recalibrate and confirm the bias hasn’t shifted.
The one caveat: all consumer BIA scales are rough tools compared to DEXA. The value isn’t in the absolute numbers — it’s in catching a trend break. If Withings shows your leg muscle rolling average dropping by 1+ lb over 2–3 months, that’s your signal to escalate training intensity or investigate before the next DEXA confirms it. Think of it as an early warning system, not a measurement device.
