Read automatically from the scorecard below — every claim can be checked against it.
Accuracy holds on the never-released cell (16.38 % vs 21.10 % on the open cells) — the model generalises rather than memorising the released data.
Cold is the weak spot: 11.11 % at −20 °C against 1.55 % at 25 °C. Below zero the cell's resistance rises and the voltage curve distorts; models without temperature awareness lose the most here.
Recovers from a wrong initial SOC (22.53 % on test 10) — the estimator pulls itself back using voltage rather than trusting its starting point.
Tolerates a biased current sensor (26.09 % on test 11) — the drift a bias causes is being corrected away.
Scorecard
Average RMSE (% SOC) per test case, weighted into the leaderboard score. Lower is better.
Estimation accuracyT1All cells(reference only — every other test is a subset of it)
19.92 %
0.0000
0.0000
T2Blinded cell (m448)
16.38 %
0.1000
1.6384
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 4.37 %, max 5.5 %
Actual SOC
AEKF - Lucas Updated
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 1.24 %, max 12.6 %
Actual SOC
AEKF - Lucas Updated
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 31.79 %, max 50.7 %
Actual SOC
AEKF - Lucas Updated
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
60.63
56.98
94.92
m80
-10 °C
HWFET
3.02 h
57.40
51.75
90.27
m80
-10 °C
LA92
4.74 h
60.13
55.56
90.62
m80
-10 °C
US06
2.30 h
53.33
47.48
85.83
m80
-10 °C
HWCUST
1.69 h
49.51
43.48
82.05
m80
-10 °C
HWGRADE
1.24 h
57.02
51.14
91.44
m80
-20 °C
UDDS
4.62 h
4.38
4.33
5.49
m80
-20 °C
HWFET
2.34 h
5.89
5.68
9.55
m80
-20 °C
LA92
3.54 h
6.02
5.32
18.54
m80
-20 °C
US06
1.86 h
5.84
5.64
9.57
m80
-20 °C
HWCUST
1.37 h
17.83
17.62
22.02
m80
-20 °C
HWGRADE
1.25 h
26.71
24.26
41.35
m80
0 °C
UDDS
8.75 h
62.72
57.60
100.00
m80
0 °C
HWFET
3.84 h
1.83
1.82
2.10
m80
0 °C
LA92
6.39 h
1.00
0.99
1.49
m80
0 °C
US06
2.93 h
3.41
3.39
3.93
m80
0 °C
HWCUST
2.08 h
4.46
4.42
6.33
m80
0 °C
HWGRADE
1.64 h
52.14
46.37
88.42
m80
10 °C
UDDS
11.32 h
1.46
1.26
2.65
m80
10 °C
HWFET
4.49 h
25.71
22.02
47.54
m80
10 °C
LA92
7.88 h
60.63
55.03
97.68
m80
10 °C
US06
3.42 h
58.42
52.32
95.59
m80
10 °C
HWCUST
2.42 h
56.47
49.55
94.70
m80
10 °C
HWGRADE
1.80 h
0.77
0.65
1.81
m80
25 °C
UDDS
16.13 h
0.30
0.26
0.74
m80
25 °C
HWFET
5.52 h
1.39
1.01
5.64
m80
25 °C
LA92
10.58 h
1.09
0.77
7.04
m80
25 °C
US06
4.22 h
1.47
1.10
7.46
m80
25 °C
HWCUST
2.86 h
2.13
1.46
8.20
m80
25 °C
HWGRADE
2.33 h
2.94
2.11
12.10
m80
40 °C
UDDS
12.40 h
0.93
0.77
2.54
m80
40 °C
HWFET
5.41 h
1.05
0.87
2.46
m80
40 °C
LA92
9.07 h
0.94
0.75
3.48
m80
40 °C
US06
4.17 h
1.40
1.15
4.13
m80
40 °C
HWCUST
2.95 h
1.50
1.31
3.28
m80
40 °C
HWGRADE
2.73 h
3.64
2.72
9.62
m448
-10 °C
UDDS
6.23 h
0.20
0.15
0.49
m448
-10 °C
HWFET
3.01 h
46.85
40.88
98.25
m448
-10 °C
LA92
4.59 h
65.58
61.79
100.00
m448
-10 °C
US06
2.25 h
64.66
60.61
100.00
m448
-10 °C
HWCUST
1.69 h
49.78
43.75
82.31
m448
-10 °C
HWGRADE
1.22 h
41.59
36.20
72.48
m448
-20 °C
UDDS
4.56 h
4.74
4.66
8.04
m448
-20 °C
HWFET
2.34 h
5.54
5.36
9.32
m448
-20 °C
LA92
3.46 h
5.76
5.63
9.56
m448
-20 °C
US06
1.80 h
6.04
5.84
9.96
m448
-20 °C
HWCUST
1.39 h
9.74
9.60
11.44
m448
-20 °C
HWGRADE
1.23 h
13.34
12.80
23.56
m448
0 °C
UDDS
8.60 h
0.12
0.11
0.33
m448
0 °C
HWFET
3.83 h
1.73
1.73
1.93
m448
0 °C
LA92
6.16 h
0.23
0.20
0.48
m448
0 °C
US06
2.87 h
61.21
55.59
100.00
m448
0 °C
HWCUST
2.09 h
0.39
0.37
0.61
m448
0 °C
HWGRADE
1.51 h
1.01
0.75
2.50
m448
10 °C
UDDS
11.08 h
1.56
1.35
2.78
m448
10 °C
HWFET
4.47 h
59.43
53.93
95.83
m448
10 °C
LA92
7.60 h
1.44
1.24
2.55
m448
10 °C
US06
3.35 h
1.31
1.10
2.54
m448
10 °C
HWCUST
2.42 h
22.19
20.75
55.78
m448
10 °C
HWGRADE
1.68 h
47.53
41.37
86.09
m448
25 °C
UDDS
15.59 h
0.30
0.24
0.83
m448
25 °C
HWFET
5.46 h
1.11
0.82
4.89
m448
25 °C
LA92
10.06 h
0.94
0.69
6.13
m448
25 °C
US06
4.07 h
1.26
0.96
7.18
m448
25 °C
HWCUST
2.86 h
1.82
1.28
7.63
m448
25 °C
HWGRADE
2.19 h
3.27
2.47
11.23
m448
40 °C
UDDS
12.09 h
1.09
0.87
3.01
m448
40 °C
HWFET
5.21 h
59.46
52.08
100.00
m448
40 °C
LA92
8.79 h
1.01
0.80
4.28
m448
40 °C
US06
4.06 h
1.52
1.24
5.02
m448
40 °C
HWCUST
2.92 h
1.55
1.36
3.38
m448
40 °C
HWGRADE
2.32 h
4.52
3.41
11.19
m448-N
-10 °C
UDDS
10.80 h
64.97
61.17
98.39
m448-N
-10 °C
HWFET
3.85 h
44.77
38.67
75.43
m448-N
-10 °C
LA92
6.66 h
58.16
54.78
88.19
m448-N
-10 °C
US06
2.70 h
58.02
51.09
97.57
m448-N
-10 °C
HWCUST
1.89 h
46.66
40.48
75.91
m448-N
-10 °C
HWGRADE
1.36 h
49.16
42.86
75.99
m448-N
-20 °C
UDDS
8.67 h
3.62
3.45
10.24
m448-N
-20 °C
HWFET
3.09 h
9.55
9.47
12.43
m448-N
-20 °C
LA92
5.21 h
3.94
3.54
11.20
m448-N
-20 °C
US06
2.23 h
33.51
32.80
41.72
m448-N
-20 °C
HWCUST
1.65 h
18.84
18.09
22.91
m448-N
-20 °C
HWGRADE
1.50 h
14.36
13.64
23.97
m448-N
0 °C
UDDS
12.79 h
0.18
0.14
0.63
m448-N
0 °C
HWFET
4.47 h
62.06
56.54
100.00
m448-N
0 °C
LA92
7.99 h
0.96
0.94
1.69
m448-N
0 °C
US06
3.22 h
0.38
0.32
0.93
m448-N
0 °C
HWCUST
2.31 h
0.72
0.70
1.12
m448-N
0 °C
HWGRADE
1.65 h
8.15
8.03
10.39
m448-N
10 °C
UDDS
13.92 h
1.34
1.18
2.40
m448-N
10 °C
HWFET
4.84 h
58.50
52.57
95.38
m448-N
10 °C
LA92
8.80 h
1.27
1.12
2.26
m448-N
10 °C
US06
3.56 h
0.93
0.78
1.97
m448-N
10 °C
HWCUST
2.53 h
18.62
10.58
60.58
m448-N
10 °C
HWGRADE
1.79 h
20.42
16.61
75.31
m448-N
25 °C
UDDS
15.61 h
0.82
0.64
5.09
m448-N
25 °C
HWFET
5.47 h
59.93
52.98
100.00
m448-N
25 °C
LA92
10.09 h
37.42
33.35
68.00
m448-N
25 °C
US06
4.08 h
0.76
0.67
1.65
m448-N
25 °C
HWCUST
2.86 h
1.78
1.25
7.42
m448-N
25 °C
HWGRADE
2.30 h
3.01
2.28
11.21
m448-N
40 °C
UDDS
16.75 h
0.59
0.51
1.32
m448-N
40 °C
HWFET
5.89 h
59.47
52.08
100.00
m448-N
40 °C
LA92
11.03 h
0.96
0.77
4.09
m448-N
40 °C
US06
4.44 h
1.07
0.96
2.12
m448-N
40 °C
HWCUST
3.13 h
1.53
1.33
3.29
m448-N
40 °C
HWGRADE
2.48 h
4.43
3.38
11.18
m1000
-10 °C
UDDS
5.91 h
65.17
61.35
97.79
m1000
-10 °C
HWFET
2.91 h
57.80
52.25
90.34
m1000
-10 °C
LA92
4.23 h
59.30
54.21
92.17
m1000
-10 °C
US06
2.09 h
64.41
60.43
100.00
m1000
-10 °C
HWCUST
1.67 h
50.15
44.16
82.45
m1000
-10 °C
HWGRADE
1.20 h
47.07
41.47
81.26
m1000
-20 °C
UDDS
4.31 h
5.85
5.75
9.61
m1000
-20 °C
HWFET
2.27 h
6.12
5.92
10.14
m1000
-20 °C
LA92
3.20 h
5.86
5.71
10.19
m1000
-20 °C
US06
1.74 h
3.32
3.28
4.07
m1000
-20 °C
HWCUST
1.37 h
35.17
29.70
66.76
m1000
-20 °C
HWGRADE
1.22 h
40.28
37.60
53.00
m1000
0 °C
UDDS
8.09 h
0.13
0.12
0.39
m1000
0 °C
HWFET
3.70 h
1.89
1.88
2.16
m1000
0 °C
LA92
5.60 h
0.27
0.24
0.56
m1000
0 °C
US06
2.66 h
3.76
3.73
4.32
m1000
0 °C
HWCUST
2.05 h
60.84
55.11
100.00
m1000
0 °C
HWGRADE
1.36 h
54.09
47.10
84.54
m1000
10 °C
UDDS
10.51 h
1.52
1.32
2.65
m1000
10 °C
HWFET
4.37 h
4.80
2.34
53.31
m1000
10 °C
LA92
7.06 h
0.74
0.60
2.86
m1000
10 °C
US06
3.11 h
2.10
1.92
14.52
m1000
10 °C
HWCUST
2.41 h
0.34
0.26
0.88
m1000
10 °C
HWGRADE
1.52 h
55.74
50.92
93.32
m1000
25 °C
UDDS
14.69 h
1.20
0.94
6.86
m1000
25 °C
HWFET
5.37 h
59.92
53.07
100.00
m1000
25 °C
LA92
9.30 h
68.66
64.82
100.00
m1000
25 °C
US06
3.79 h
1.41
1.05
8.55
m1000
25 °C
HWCUST
2.83 h
2.26
1.54
9.05
m1000
25 °C
HWGRADE
1.90 h
3.81
2.89
12.94
m1000
40 °C
UDDS
11.69 h
1.17
0.95
3.08
m1000
40 °C
HWFET
5.15 h
1.03
0.83
2.69
m1000
40 °C
LA92
8.33 h
1.02
0.82
4.37
m1000
40 °C
US06
3.89 h
1.47
1.20
5.00
m1000
40 °C
HWCUST
2.91 h
1.30
1.12
3.14
m1000
40 °C
HWGRADE
2.17 h
5.35
4.11
12.90
m80 UDDS at -20 °C
Whole cycle · RMSE 4.37 %, max 5.5 %
Actual SOC
AEKF - Lucas Updated
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).
AEKF model of Lucas after changing parameters at 10, 0, -10 and -20 degree C
Package
Lucas_Model_Updated.zip (14.2 KB) — deleted after evaluation
Visibility
Public
Evaluator
socbench-eval-0.1.0/matlab
Completed
Sep 2, 2026, 04:39 p.m. EDT
Submission ID
cmtkk6e8i0001jo042n9zrr75
Non-blinded cells
21.10 %
0.1000
2.1099
Operating conditionsT4Charging
6.38 %
0.1000
0.6375
T580 kg payload
20.90 %
0.0333
0.6967
T5448 kg payload, HVAC on
16.38 %
0.0667
1.0923
T6448 kg payload, HVAC off
20.86 %
0.0667
1.3905
T51000 kg payload
21.54 %
0.0333
0.7179
T7Standard drive cycles
19.30 %
0.1000
1.9298
T8Non-standard drive cycles
21.16 %
0.1000
2.1165
T9−20 °C
11.11 %
0.0167
0.1852
T9−10 °C
56.34 %
0.0167
0.9389
T90 °C
20.93 %
0.0167
0.3488
T910 °C
33.91 %
0.0167
0.5651
T925 °C
1.55 %
0.0167
0.0259
T940 °C
1.58 %
0.0167
0.0263
RobustnessT10Initial SOC error
22.53 %
0.1000
2.2527
T11Current sensor offset
26.09 %
0.1000
2.6093
Weighted error = Σ (weight × RMSE)
19.28 %
Max error 100.0 % — largest instantaneous |estimate − truth| over every blinded cycle (on m80 UDDS at 0 °C — plotted under Key cases for new evaluations); not scoredComplexity 7 ±1 · High (informational, not scored)
Ahnaf Rahman · McMaster University