First Model

Completed

14.84 %weighted error Rank #9#70 · Coulomb counter · Aug 27, 2026, 05:12 p.m. EDT

Paarth Kadakia · McMaster University

What these results say

Read automatically from the scorecard below — every claim can be checked against it.

75 % of the score comes from charging (T4, 80.65 % × weight 0.100) and initial soc error (T10, 30.54 % × weight 0.100) — improving there moves the leaderboard position most.
Accuracy holds on the never-released cell (1.67 % vs 1.79 % on the open cells) — the model generalises rather than memorising the released data.
Cold is the weak spot: 2.73 % at −20 °C against 0.44 % at 25 °C. Below zero the cell's resistance rises and the voltage curve distorts; models without temperature awareness lose the most here.
Charging is much worse than driving (80.65 % vs 1.76 % overall) — typical of estimators tuned only on discharge behaviour.
A wrong initial SOC is not corrected: 30.54 % on test 10. Pure current integration can never recover from a bad start; voltage feedback is what fixes this.

Scorecard

Average RMSE (% SOC) per test case, weighted into the leaderboard score. Lower is better.

Weighted error

14.84 %

Test case	RMSE	Weight	Weight × RMSE
Estimation accuracyT1All cells(reference only — every other test is a subset of it)	1.76 %	0.0000	0.0000
T2Blinded cell (m448)	1.67 %	0.1000	0.1667
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.

Robustness-case traces were not recorded for this result

This submission was evaluated before the evaluator stored the initial-SOC and sensor-offset traces (2026-08-29). The drive-cycle traces below are complete; submit a new version to get the robustness plots as well.

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 2.51 %, max 4.5 %

Actual SOC
First Model

Drive cycle

Error axis Fit SOC axis (error axis fits itself when set to Auto)

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

Temperature

Cycle

Cell	Temp.	Cycle	Duration	RMSE	MAE	MAXE
m80	-10 °C	UDDS	6.32 h	2.37	1.95	4.31
m80	-10 °C	HWFET	3.02 h	2.51	2.08	4.41
m80	-10 °C	LA92	4.74 h	2.37	1.93	4.32
m80	-10 °C	US06	2.30 h	2.55	2.10	4.44
m80	-10 °C	HWCUST	1.69 h	2.97	2.49	4.92
m80	-10 °C	HWGRADE	1.24 h	2.99	2.48	5.01
m80	-20 °C	UDDS	4.62 h	2.51	2.07	4.50
m80	-20 °C	HWFET	2.34 h	2.64	2.18	4.55
m80	-20 °C	LA92	3.54 h	2.39	1.96	4.28
m80	-20 °C	US06	1.86 h	2.67	2.21	4.50
m80	-20 °C	HWCUST	1.37 h	2.98	2.50	4.77
m80	-20 °C	HWGRADE	1.25 h	3.20	2.76	4.84
m80	0 °C	UDDS	8.75 h	2.29	1.87	4.22
m80	0 °C	HWFET	3.84 h	2.43	2.00	4.34
m80	0 °C	LA92	6.39 h	2.27	1.86	4.18
m80	0 °C	US06	2.93 h	2.38	1.96	4.21
m80	0 °C	HWCUST	2.08 h	2.80	2.33	4.77
m80	0 °C	HWGRADE	1.64 h	3.02	2.50	4.86
m80	10 °C	UDDS	11.32 h	1.04	0.84	2.04
m80	10 °C	HWFET	4.49 h	1.23	1.00	2.29
m80	10 °C	LA92	7.88 h	1.11	0.90	2.18
m80	10 °C	US06	3.42 h	1.45	1.18	2.66
m80	10 °C	HWCUST	2.42 h	2.25	1.86	3.85
m80	10 °C	HWGRADE	1.80 h	2.46	2.03	4.15
m80	25 °C	UDDS	16.13 h	0.27	0.23	0.52
m80	25 °C	HWFET	5.52 h	0.28	0.24	0.50
m80	25 °C	LA92	10.58 h	0.29	0.25	0.51
m80	25 °C	US06	4.22 h	0.30	0.26	0.51
m80	25 °C	HWCUST	2.86 h	0.71	0.58	1.33
m80	25 °C	HWGRADE	2.33 h	0.80	0.65	1.51
m80	40 °C	UDDS	12.40 h	1.54	1.43	2.42
m80	40 °C	HWFET	5.41 h	1.45	1.36	2.23
m80	40 °C	LA92	9.07 h	1.36	1.27	2.15
m80	40 °C	US06	4.17 h	1.40	1.32	2.09
m80	40 °C	HWCUST	2.95 h	0.58	0.58	0.64
m80	40 °C	HWGRADE	2.73 h	0.41	0.41	0.50
m448	-10 °C	UDDS	6.23 h	2.07	1.71	3.73
m448	-10 °C	HWFET	3.01 h	2.16	1.78	3.81
m448	-10 °C	LA92	4.59 h	1.90	1.54	3.48
m448	-10 °C	US06	2.25 h	2.03	1.66	3.60
m448	-10 °C	HWCUST	1.69 h	2.58	2.16	4.32
m448	-10 °C	HWGRADE	1.22 h	2.72	2.27	4.44
m448	-20 °C	UDDS	4.56 h	2.15	1.77	3.88
m448	-20 °C	HWFET	2.34 h	2.28	1.88	3.97
m448	-20 °C	LA92	3.46 h	1.99	1.62	3.62
m448	-20 °C	US06	1.80 h	2.19	1.80	3.81
m448	-20 °C	HWCUST	1.39 h	2.62	2.20	4.20
m448	-20 °C	HWGRADE	1.23 h	2.84	2.46	4.25
m448	0 °C	UDDS	8.60 h	2.12	1.73	3.96
m448	0 °C	HWFET	3.83 h	2.26	1.86	4.05
m448	0 °C	LA92	6.16 h	2.04	1.67	3.77
m448	0 °C	US06	2.87 h	2.15	1.76	3.82
m448	0 °C	HWCUST	2.09 h	2.43	2.02	4.16
m448	0 °C	HWGRADE	1.51 h	2.55	2.12	4.20
m448	10 °C	UDDS	11.08 h	0.97	0.78	1.94
m448	10 °C	HWFET	4.47 h	1.13	0.91	2.13
m448	10 °C	LA92	7.60 h	1.08	0.88	2.19
m448	10 °C	US06	3.35 h	1.21	0.98	2.27
m448	10 °C	HWCUST	2.42 h	2.15	1.78	3.70
m448	10 °C	HWGRADE	1.68 h	2.31	1.90	3.93
m448	25 °C	UDDS	15.59 h	0.30	0.25	0.53
m448	25 °C	HWFET	5.46 h	0.26	0.22	0.50
m448	25 °C	LA92	10.06 h	0.30	0.27	0.54
m448	25 °C	US06	4.07 h	0.47	0.39	0.85
m448	25 °C	HWCUST	2.86 h	0.65	0.54	1.23
m448	25 °C	HWGRADE	2.19 h	0.71	0.57	1.35
m448	40 °C	UDDS	12.09 h	1.65	1.53	2.63
m448	40 °C	HWFET	5.21 h	1.55	1.45	2.43
m448	40 °C	LA92	8.79 h	1.57	1.48	2.36
m448	40 °C	US06	4.06 h	1.52	1.43	2.24
m448	40 °C	HWCUST	2.92 h	0.63	0.62	0.73
m448	40 °C	HWGRADE	2.32 h	0.45	0.45	0.51
m448-N	-10 °C	UDDS	10.80 h	2.14	1.73	4.03
m448-N	-10 °C	HWFET	3.85 h	2.49	2.06	4.44
m448-N	-10 °C	LA92	6.66 h	2.16	1.76	4.03
m448-N	-10 °C	US06	2.70 h	2.32	1.90	4.07
m448-N	-10 °C	HWCUST	1.89 h	2.92	2.44	4.95
m448-N	-10 °C	HWGRADE	1.36 h	3.14	2.63	5.05
m448-N	-20 °C	UDDS	8.67 h	2.19	1.77	4.16
m448-N	-20 °C	HWFET	3.09 h	2.58	2.12	4.57
m448-N	-20 °C	LA92	5.21 h	2.10	1.70	3.94
m448-N	-20 °C	US06	2.23 h	2.66	2.20	4.54
m448-N	-20 °C	HWCUST	1.65 h	3.03	2.56	4.84
m448-N	-20 °C	HWGRADE	1.50 h	3.30	2.90	4.88
m448-N	0 °C	UDDS	12.79 h	2.39	1.96	4.47
m448-N	0 °C	HWFET	4.47 h	2.60	2.14	4.65
m448-N	0 °C	LA92	7.99 h	2.40	1.94	4.46
m448-N	0 °C	US06	3.22 h	2.50	2.06	4.44
m448-N	0 °C	HWCUST	2.31 h	2.87	2.40	4.84
m448-N	0 °C	HWGRADE	1.65 h	3.08	2.57	4.91
m448-N	10 °C	UDDS	13.92 h	1.21	0.97	2.34
m448-N	10 °C	HWFET	4.84 h	1.42	1.15	2.65
m448-N	10 °C	LA92	8.80 h	1.27	1.01	2.52
m448-N	10 °C	US06	3.56 h	1.57	1.27	2.83
m448-N	10 °C	HWCUST	2.53 h	2.53	2.11	4.34
m448-N	10 °C	HWGRADE	1.79 h	2.76	2.29	4.56
m448-N	25 °C	UDDS	15.61 h	0.40	0.34	0.80
m448-N	25 °C	HWFET	5.47 h	0.43	0.36	0.85
m448-N	25 °C	LA92	10.09 h	0.42	0.35	0.84
m448-N	25 °C	US06	4.08 h	0.44	0.38	0.84
m448-N	25 °C	HWCUST	2.86 h	0.94	0.76	1.74
m448-N	25 °C	HWGRADE	2.30 h	1.06	0.86	1.89
m448-N	40 °C	UDDS	16.75 h	1.43	1.34	2.23
m448-N	40 °C	HWFET	5.89 h	1.34	1.26	2.03
m448-N	40 °C	LA92	11.03 h	1.30	1.23	1.98
m448-N	40 °C	US06	4.44 h	1.14	1.08	1.67
m448-N	40 °C	HWCUST	3.13 h	0.42	0.41	0.53
m448-N	40 °C	HWGRADE	2.48 h	0.28	0.23	0.50
m1000	-10 °C	UDDS	5.91 h	2.00	1.63	3.67
m1000	-10 °C	HWFET	2.91 h	2.21	1.82	3.94
m1000	-10 °C	LA92	4.23 h	1.86	1.51	3.41
m1000	-10 °C	US06	2.09 h	2.14	1.75	3.75
m1000	-10 °C	HWCUST	1.67 h	2.67	2.23	4.43
m1000	-10 °C	HWGRADE	1.20 h	2.95	2.51	4.56
m1000	-20 °C	UDDS	4.31 h	2.16	1.76	3.88
m1000	-20 °C	HWFET	2.27 h	2.37	1.95	4.13
m1000	-20 °C	LA92	3.20 h	2.00	1.62	3.60
m1000	-20 °C	US06	1.74 h	1.44	1.25	2.83
m1000	-20 °C	HWCUST	1.37 h	2.67	2.24	4.27
m1000	-20 °C	HWGRADE	1.22 h	3.00	2.63	4.39
m1000	0 °C	UDDS	8.09 h	2.10	1.71	3.90
m1000	0 °C	HWFET	3.70 h	2.29	1.88	4.09
m1000	0 °C	LA92	5.60 h	1.97	1.59	3.75
m1000	0 °C	US06	2.66 h	2.19	1.79	3.86
m1000	0 °C	HWCUST	2.05 h	2.49	2.06	4.26
m1000	0 °C	HWGRADE	1.36 h	2.64	2.19	4.32
m1000	10 °C	UDDS	10.51 h	1.01	0.81	2.05
m1000	10 °C	HWFET	4.37 h	1.26	1.02	2.37
m1000	10 °C	LA92	7.06 h	1.13	0.89	2.28
m1000	10 °C	US06	3.11 h	1.19	0.93	2.28
m1000	10 °C	HWCUST	2.41 h	2.22	1.84	3.81
m1000	10 °C	HWGRADE	1.52 h	2.42	2.00	4.02
m1000	25 °C	UDDS	14.69 h	0.28	0.23	0.54
m1000	25 °C	HWFET	5.37 h	0.32	0.28	0.54
m1000	25 °C	LA92	9.30 h	0.32	0.27	0.51
m1000	25 °C	US06	3.79 h	0.47	0.41	0.91
m1000	25 °C	HWCUST	2.83 h	0.78	0.63	1.47
m1000	25 °C	HWGRADE	1.90 h	0.78	0.62	1.48
m1000	40 °C	UDDS	11.69 h	1.51	1.41	2.36
m1000	40 °C	HWFET	5.15 h	1.46	1.36	2.25
m1000	40 °C	LA92	8.33 h	1.31	1.25	1.95
m1000	40 °C	US06	3.89 h	1.15	1.10	1.68
m1000	40 °C	HWCUST	2.91 h	0.53	0.53	0.54
m1000	40 °C	HWGRADE	2.17 h	0.38	0.38	0.51

m80 UDDS at -20 °C

Whole cycle · RMSE 2.51 %, max 4.5 %

Actual SOC
First Model

Drive cycle

Error axis Fit SOC axis (error axis fits itself when set to Auto)

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.

Aug 27, 2026, 05:12 p.m. EDTEvaluated · socbench-eval-0.1.0v1 · attempt 114.84 %

How a coulomb counter worksThe canonical structure for this model family; the author's description below gives the specific architecture.

Coulomb counter — standardized view

Open-loop current integration

Governing equation

\mathrm{SOC}_k = \mathrm{SOC}_{k-1} + \frac{I_k\,\Delta t}{3600\, C_n}

Downloads

PDF report (summary, every test case with the arithmetic, key plots, per-cycle table) · results as JSON · full-resolution traces are stored for evaluations from 2026-08-30 onward — submit a new version to get them.

PDF report JSON

About this submission

Coulomb Counter Model

Package: model.zip (7.6 KB) — deleted after evaluation
Visibility: Public
Evaluator: socbench-eval-0.1.0/python
Completed: Aug 27, 2026, 05:12 p.m. EDT
Submission ID: cmtc0qzuq0007ju04uwb20reb