Estimation accuracyT1All cells(reference only — every other test is a subset of it)
2.80 %
0.0000
0.0000
T2Blinded cell (m448)
2.58 %
0.1000
0.2575
T3
Key cases
The runs that separate estimators — cold and hot cycles, the blinded cell, wrong initial SOC, a biased current sensor. Each plot says why it is there.
Selected drive cycles
The thirteen cycles the original MATLAB tool plotted, one per test: blinded vs non-blinded cell (tests 1–3), drive vs charge (test 4), the three payloads on one cycle (tests 5–6), standard vs non-standard highway profiles (tests 7–8) and the temperature extremes (test 9).
m80 UDDS at -20 °C
Whole cycle · RMSE 2.59 %, max 7.6 %
Actual SOC
Wisconsin - Old
Error axis
Why this case: Test 9 — coldest condition: high resistance and a strongly non-linear OCV response — the hardest cycle for most estimators.
Wrong initial SOC (test 10)
Three cycles restarted with the estimator told the battery is at 90, 60 or 30 % while it is really full. Coulomb counting can never recover; voltage-informed estimators converge at a rate that is very visible here.
Wrong initial SOC 90 % — m80 LA92 at 25 °C
Whole cycle · RMSE 2.43 %, max 9.5 %
Actual SOC
Wisconsin - Old
Error axis
Why this case: The cycle is joined at the point where the true SOC has already fallen to 90 %, so a model that assumes a full battery at start-up begins 10 % off. What matters is how fast the estimate converges onto the truth.
Current-sensor offset (test 11)
Three cycles re-run with ±0.3 A added to the measured current. Integration-based estimators drift steadily; the plot shows whether and how fast the model corrects the bias.
Current-sensor offset -0.3 A — m1000 US06 at -10 °C
Whole cycle · RMSE 2.40 %, max 6.1 %
Actual SOC
Wisconsin - Old
Error axis
Why this case: A constant -0.3 A is added to the measured current before it reaches the model. Pure current integration drifts linearly; estimators that also use voltage should correct it.
RMSE vs. sensor offset
Test 11 — the same three cycles re-run with a constant current offset; 0 A is the unmodified run. Only ±0.3 A enters the score.
US06 at −10 °C
HWFET at 10 °C
LA92 at 40 °C
Test-case chartsThe scorecard as bar charts — tests 1–8, and RMSE against temperature (test 9).
Error by test case
Average RMS error (% SOC) for each blinded test case. Lower is better.
Error vs. ambient temperature
Test 9 — m80 cell, all blinded cycles at each chamber temperature.
All 144 cyclesEvery blinded drive cycle: per-cycle errors, and any of the plotted cycles in the time domain.
Cell
Temp.
Cycle
Duration
RMSE
MAE
MAXE
m80
-10 °C
UDDS
6.32 h
1.95
1.55
5.28
m80
-10 °C
HWFET
3.02 h
4.95
3.83
12.68
m80
-10 °C
LA92
4.74 h
1.57
1.20
5.68
m80
-10 °C
US06
2.30 h
3.05
2.61
6.54
m80
-10 °C
HWCUST
1.69 h
5.55
4.46
11.89
m80
-10 °C
HWGRADE
1.24 h
4.54
3.73
11.07
m80
-20 °C
UDDS
4.62 h
2.48
2.02
7.64
m80
-20 °C
HWFET
2.34 h
6.65
5.83
14.89
m80
-20 °C
LA92
3.54 h
1.97
1.58
5.85
m80
-20 °C
US06
1.86 h
2.99
2.50
6.86
m80
-20 °C
HWCUST
1.37 h
5.46
4.68
17.35
m80
-20 °C
HWGRADE
1.25 h
5.14
4.35
10.89
m80
0 °C
UDDS
8.75 h
1.98
1.74
4.92
m80
0 °C
HWFET
3.84 h
1.72
1.40
4.79
m80
0 °C
LA92
6.39 h
1.18
0.88
3.95
m80
0 °C
US06
2.93 h
2.07
1.75
4.86
m80
0 °C
HWCUST
2.08 h
3.28
2.45
10.46
m80
0 °C
HWGRADE
1.64 h
3.17
2.59
7.07
m80
10 °C
UDDS
11.32 h
1.52
1.21
4.36
m80
10 °C
HWFET
4.49 h
1.36
1.13
3.24
m80
10 °C
LA92
7.88 h
1.32
1.08
3.68
m80
10 °C
US06
3.42 h
1.17
0.94
3.09
m80
10 °C
HWCUST
2.42 h
2.22
1.89
5.42
m80
10 °C
HWGRADE
1.80 h
3.10
2.55
9.98
m80
25 °C
UDDS
16.13 h
2.65
2.29
6.17
m80
25 °C
HWFET
5.52 h
2.71
2.18
6.81
m80
25 °C
LA92
10.58 h
2.17
1.81
5.79
m80
25 °C
US06
4.22 h
2.38
2.08
5.59
m80
25 °C
HWCUST
2.86 h
2.28
1.85
5.64
m80
25 °C
HWGRADE
2.33 h
3.16
2.59
8.61
m80
40 °C
UDDS
12.40 h
2.26
1.98
4.83
m80
40 °C
HWFET
5.41 h
4.69
2.39
70.57
m80
40 °C
LA92
9.07 h
2.08
1.78
4.74
m80
40 °C
US06
4.17 h
2.56
2.19
6.03
m80
40 °C
HWCUST
2.95 h
3.67
3.23
7.17
m80
40 °C
HWGRADE
2.73 h
3.48
2.88
8.72
m448
-10 °C
UDDS
6.23 h
1.37
1.13
3.62
m448
-10 °C
HWFET
3.01 h
4.11
3.19
10.33
m448
-10 °C
LA92
4.59 h
1.15
0.90
4.50
m448
-10 °C
US06
2.25 h
2.98
2.50
6.39
m448
-10 °C
HWCUST
1.69 h
2.90
2.18
11.10
m448
-10 °C
HWGRADE
1.22 h
4.12
3.39
9.99
m448
-20 °C
UDDS
4.56 h
1.66
1.27
5.92
m448
-20 °C
HWFET
2.34 h
4.91
4.30
11.17
m448
-20 °C
LA92
3.46 h
1.63
1.33
5.39
m448
-20 °C
US06
1.80 h
2.79
2.33
6.34
m448
-20 °C
HWCUST
1.39 h
4.64
3.95
16.15
m448
-20 °C
HWGRADE
1.23 h
4.59
3.87
10.01
m448
0 °C
UDDS
8.60 h
2.24
2.07
5.03
m448
0 °C
HWFET
3.83 h
1.64
1.30
4.46
m448
0 °C
LA92
6.16 h
1.25
1.00
3.72
m448
0 °C
US06
2.87 h
1.74
1.41
4.52
m448
0 °C
HWCUST
2.09 h
2.73
2.00
9.84
m448
0 °C
HWGRADE
1.51 h
3.44
2.84
7.79
m448
10 °C
UDDS
11.08 h
1.76
1.41
4.89
m448
10 °C
HWFET
4.47 h
1.26
1.08
2.98
m448
10 °C
LA92
7.60 h
1.43
1.15
4.03
m448
10 °C
US06
3.35 h
1.19
0.95
3.30
m448
10 °C
HWCUST
2.42 h
2.35
1.96
5.52
m448
10 °C
HWGRADE
1.68 h
3.72
3.10
8.52
m448
25 °C
UDDS
15.59 h
2.04
1.65
5.67
m448
25 °C
HWFET
5.46 h
2.72
2.23
6.95
m448
25 °C
LA92
10.06 h
2.07
1.74
5.65
m448
25 °C
US06
4.07 h
2.40
2.13
5.13
m448
25 °C
HWCUST
2.86 h
2.33
1.84
6.03
m448
25 °C
HWGRADE
2.19 h
3.49
2.84
9.60
m448
40 °C
UDDS
12.09 h
2.11
1.86
4.61
m448
40 °C
HWFET
5.21 h
2.44
2.06
5.45
m448
40 °C
LA92
8.79 h
1.92
1.64
4.62
m448
40 °C
US06
4.06 h
2.38
2.00
5.90
m448
40 °C
HWCUST
2.92 h
3.56
3.12
7.23
m448
40 °C
HWGRADE
2.32 h
3.64
2.98
9.63
m448-N
-10 °C
UDDS
10.80 h
4.14
3.96
6.62
m448-N
-10 °C
HWFET
3.85 h
3.18
2.50
9.88
m448-N
-10 °C
LA92
6.66 h
2.96
2.76
5.74
m448-N
-10 °C
US06
2.70 h
1.57
1.23
4.32
m448-N
-10 °C
HWCUST
1.89 h
3.10
2.55
10.52
m448-N
-10 °C
HWGRADE
1.36 h
4.19
3.45
10.07
m448-N
-20 °C
UDDS
8.67 h
7.21
6.46
20.31
m448-N
-20 °C
HWFET
3.09 h
9.71
5.55
67.31
m448-N
-20 °C
LA92
5.21 h
2.68
2.30
7.16
m448-N
-20 °C
US06
2.23 h
2.67
2.15
6.91
m448-N
-20 °C
HWCUST
1.65 h
4.72
4.01
11.37
m448-N
-20 °C
HWGRADE
1.50 h
4.70
3.77
15.67
m448-N
0 °C
UDDS
12.79 h
3.84
3.66
6.98
m448-N
0 °C
HWFET
4.47 h
1.79
1.38
4.92
m448-N
0 °C
LA92
7.99 h
2.42
2.22
4.75
m448-N
0 °C
US06
3.22 h
1.29
1.03
3.62
m448-N
0 °C
HWCUST
2.31 h
2.70
2.01
9.29
m448-N
0 °C
HWGRADE
1.65 h
3.60
2.99
8.85
m448-N
10 °C
UDDS
13.92 h
2.45
2.11
5.76
m448-N
10 °C
HWFET
4.84 h
1.28
1.08
3.12
m448-N
10 °C
LA92
8.80 h
1.88
1.58
4.76
m448-N
10 °C
US06
3.56 h
1.35
1.07
3.55
m448-N
10 °C
HWCUST
2.53 h
2.34
1.96
5.22
m448-N
10 °C
HWGRADE
1.79 h
3.56
2.94
10.05
m448-N
25 °C
UDDS
15.61 h
2.29
1.92
5.87
m448-N
25 °C
HWFET
5.47 h
2.84
2.37
7.04
m448-N
25 °C
LA92
10.09 h
2.24
1.93
5.78
m448-N
25 °C
US06
4.08 h
2.49
2.22
5.21
m448-N
25 °C
HWCUST
2.86 h
2.32
1.83
6.00
m448-N
25 °C
HWGRADE
2.30 h
3.48
2.83
9.76
m448-N
40 °C
UDDS
16.75 h
2.19
1.93
4.60
m448-N
40 °C
HWFET
5.89 h
2.44
2.08
5.31
m448-N
40 °C
LA92
11.03 h
1.98
1.69
4.68
m448-N
40 °C
US06
4.44 h
2.37
2.00
5.74
m448-N
40 °C
HWCUST
3.13 h
3.40
2.95
6.78
m448-N
40 °C
HWGRADE
2.48 h
3.79
3.13
9.36
m1000
-10 °C
UDDS
5.91 h
1.30
1.08
3.36
m1000
-10 °C
HWFET
2.91 h
3.88
3.11
10.64
m1000
-10 °C
LA92
4.23 h
0.98
0.78
3.32
m1000
-10 °C
US06
2.09 h
3.43
2.99
8.00
m1000
-10 °C
HWCUST
1.67 h
3.30
2.58
12.62
m1000
-10 °C
HWGRADE
1.20 h
4.85
4.03
10.91
m1000
-20 °C
UDDS
4.31 h
1.67
1.28
5.79
m1000
-20 °C
HWFET
2.27 h
3.75
3.15
9.74
m1000
-20 °C
LA92
3.20 h
1.79
1.47
6.14
m1000
-20 °C
US06
1.74 h
2.42
1.97
7.29
m1000
-20 °C
HWCUST
1.37 h
3.60
2.92
14.99
m1000
-20 °C
HWGRADE
1.22 h
5.41
4.49
11.84
m1000
0 °C
UDDS
8.09 h
2.40
2.25
5.23
m1000
0 °C
HWFET
3.70 h
1.52
1.28
3.76
m1000
0 °C
LA92
5.60 h
1.47
1.27
4.17
m1000
0 °C
US06
2.66 h
1.58
1.30
4.22
m1000
0 °C
HWCUST
2.05 h
3.52
2.83
10.69
m1000
0 °C
HWGRADE
1.36 h
4.58
3.75
10.35
m1000
10 °C
UDDS
10.51 h
2.00
1.67
5.13
m1000
10 °C
HWFET
4.37 h
1.20
1.02
3.28
m1000
10 °C
LA92
7.06 h
1.55
1.28
4.34
m1000
10 °C
US06
3.11 h
1.22
0.97
3.47
m1000
10 °C
HWCUST
2.41 h
1.90
1.55
7.15
m1000
10 °C
HWGRADE
1.52 h
4.55
3.76
11.60
m1000
25 °C
UDDS
14.69 h
2.03
1.66
5.58
m1000
25 °C
HWFET
5.37 h
2.40
1.93
6.30
m1000
25 °C
LA92
9.30 h
1.97
1.63
5.42
m1000
25 °C
US06
3.79 h
2.31
2.01
4.63
m1000
25 °C
HWCUST
2.83 h
1.80
1.40
4.83
m1000
25 °C
HWGRADE
1.90 h
4.21
3.40
10.60
m1000
40 °C
UDDS
11.69 h
2.08
1.83
4.47
m1000
40 °C
HWFET
5.15 h
2.32
1.98
5.24
m1000
40 °C
LA92
8.33 h
1.83
1.53
4.70
m1000
40 °C
US06
3.89 h
2.32
1.98
5.48
m1000
40 °C
HWCUST
2.91 h
3.17
2.79
6.31
m1000
40 °C
HWGRADE
2.17 h
4.16
3.33
11.60
m80 UDDS at -20 °C
Whole cycle · RMSE 2.59 %, max 7.6 %
Actual SOC
Wisconsin - Old
Error axis
One hour of padded data precedes every cycle in the evaluator and is excluded from the error metrics. Charts are down-sampled for display (peaks preserved); the full 1 Hz data is in the traces download below.
Score historyEvery evaluation attempt and every change to how this submission is scored; the current score is the last row.
How a other worksThe canonical structure for this model family; the author's description below gives the specific architecture.
Other — standardized view
Unspecified
Governing equation
[Y,z]=Model(X,z)
Downloads
PDF report (summary, every test case with the arithmetic, key plots, per-cycle table) · results as JSON · full 1 Hz traces of all 195 runs as a MATLAB v7 file (0.01 % SOC steps; readable with scipy.io.loadmat, see the readme variable inside).
Wisconsin_Old.zip (13.6 KB) — deleted after evaluation
Visibility
Public
Evaluator
socbench-eval-0.1.0/matlab
Completed
Aug 31, 2026, 12:50 p.m. EDT
Submission ID
cmthfchdd0007ky04fwa9x7jn
Non-blinded cells
2.87 %
0.1000
0.2872
Operating conditionsT4Charging
2.18 %
0.1000
0.2178
T580 kg payload
2.90 %
0.0333
0.0968
T5448 kg payload, HVAC on
2.58 %
0.0667
0.1717
T6448 kg payload, HVAC off
3.09 %
0.0667
0.2059
T51000 kg payload
2.62 %
0.0333
0.0875
T7Standard drive cycles
2.39 %
0.1000
0.2388
T8Non-standard drive cycles
3.62 %
0.1000
0.3616
T9−20 °C
4.12 %
0.0167
0.0686
T9−10 °C
3.60 %
0.0167
0.0601
T90 °C
2.23 %
0.0167
0.0372
T910 °C
1.78 %
0.0167
0.0297
T925 °C
2.56 %
0.0167
0.0427
T940 °C
3.12 %
0.0167
0.0521
RobustnessT10Initial SOC error
3.97 %
0.1000
0.3972
T11Current sensor offset
2.63 %
0.1000
0.2630
Weighted error = Σ (weight × RMSE)
2.88 %
Max error 70.6 % — largest instantaneous |estimate − truth| over every blinded cycle (on m80 HWFET at 40 °C — plotted under Key cases for new evaluations); not scoredComplexity 10 ±1 · Extreme+ (informational, not scored)
Ahnaf Rahman · McMaster University