LONG-HORIZON AGENT EVALUATION

TCG-Bench

Can an AI run a profitable card store?

POKÉMON · MAGIC · YU-GI-OH! · GUNDAM
BASELINE TRIAL
365 days
STARTING CAPITAL
$100,000
ANNUAL RUNS
1

TCG-Bench puts AI agents in charge of a simulated trading-card store: sourcing stock, setting prices, managing inventory, and keeping cash available. Long runs test whether good decisions persist through operating costs, delivery delays, and changing markets.

One score: ending cash + inventory value. Each run starts with $100,000; higher is better. The current baseline is GPT-OSS 20B with planning tools, from one replay-verified, complete 365-day simulation.

365-DAY BENCHMARK

GPT-OSS 20B

With planning tools · Mac mini · one complete annual run

365 / 365 DAYS · REPLAY VERIFIED
FINAL SCORE · TOTAL ASSETS$165,641.50

Score = cash + inventory value

Ending cash
$156,949.92
Ending inventory value
$8,691.58

$65,641.50 above the $100,000 starting capital (+65.64%).

Inventory valued at simulated liquidation bids after selling costs.

Cash and inventory over 365 days

GPT-OSS 20B + planner · recorded end-of-day values

Simulation day (end of day)

Bank balanceInventory valueScore · cash + inventory

Score = cash + inventory liquidation value after selling costs. Starting capital funds opening stock. The chart shows recorded end-of-day values, starting on day 1.

View daily values as a table
DayBank balanceInventory valueScore · cash + inventory
1$60,476.68$15,919.59$76,396.27
2$61,510.49$15,577.41$77,087.90
3$63,425.38$15,372.04$78,797.42
4$65,060.84$15,579.94$80,640.78
5$66,819.26$15,228.58$82,047.84
6$69,139.11$15,273.88$84,412.99
7$71,337.79$14,886.11$86,223.90
8$73,056.53$14,479.70$87,536.23
9$74,337.14$14,175.15$88,512.29
10$76,429.19$13,721.65$90,150.84
11$78,520.99$13,229.86$91,750.85
12$79,614.97$13,057.40$92,672.37
13$80,842.09$12,813.57$93,655.66
14$82,220.84$12,484.61$94,705.45
15$82,966.00$12,275.32$95,241.32
16$84,258.24$12,184.71$96,442.95
17$86,250.64$11,709.83$97,960.47
18$87,147.74$11,830.75$98,978.49
19$87,761.84$11,706.66$99,468.50
20$89,517.82$10,757.10$100,274.92
21$90,262.39$10,475.21$100,737.60
22$91,607.87$10,106.32$101,714.19
23$91,962.43$9,735.72$101,698.15
24$92,488.87$9,486.76$101,975.63
25$93,049.63$9,424.89$102,474.52
26$89,848.29$9,214.08$99,062.37
27$90,241.29$9,406.79$99,648.08
28$90,404.35$9,190.71$99,595.06
29$90,859.36$8,854.51$99,713.87
30$91,143.58$8,851.41$99,994.99
31$91,311.05$9,098.18$100,409.23
32$91,766.19$9,114.33$100,880.52
33$92,033.43$9,330.98$101,364.41
34$92,688.17$8,779.70$101,467.87
35$93,183.48$8,575.86$101,759.34
36$93,531.50$8,390.33$101,921.83
37$93,911.55$8,458.19$102,369.74
38$94,323.31$8,475.85$102,799.16
39$94,239.95$8,406.64$102,646.59
40$94,775.67$8,460.86$103,236.53
41$95,627.40$7,935.75$103,563.15
42$95,905.22$7,856.55$103,761.77
43$96,539.78$8,667.45$105,207.23
44$96,780.05$8,513.12$105,293.17
45$96,915.07$8,169.26$105,084.33
46$97,196.22$8,777.59$105,973.81
47$97,601.19$9,146.51$106,747.70
48$98,326.94$9,009.09$107,336.03
49$98,682.31$9,440.93$108,123.24
50$98,927.29$9,365.64$108,292.93
51$99,238.54$8,701.51$107,940.05
52$99,493.56$8,643.61$108,137.17
53$100,255.35$9,209.97$109,465.32
54$100,709.78$8,482.95$109,192.73
55$101,115.70$8,700.27$109,815.97
56$102,345.07$8,517.47$110,862.54
57$97,529.28$8,394.44$105,923.72
58$97,657.56$8,284.95$105,942.51
59$97,945.26$8,296.54$106,241.80
60$98,391.73$7,499.27$105,891.00
61$98,707.69$8,317.34$107,025.03
62$99,372.96$8,284.05$107,657.01
63$98,936.53$7,213.70$106,150.23
64$99,088.33$7,248.88$106,337.21
65$99,400.29$8,779.10$108,179.39
66$99,510.79$9,279.52$108,790.31
67$99,765.06$8,839.74$108,604.80
68$100,114.43$8,714.64$108,829.07
69$100,350.12$9,637.90$109,988.02
70$101,201.90$9,181.34$110,383.24
71$101,795.45$9,215.74$111,011.19
72$101,917.00$9,407.36$111,324.36
73$102,221.01$9,103.78$111,324.79
74$102,334.13$9,153.90$111,488.03
75$102,803.02$9,016.90$111,819.92
76$103,085.91$8,746.78$111,832.69
77$103,409.26$8,478.13$111,887.39
78$103,863.27$9,482.85$113,346.12
79$105,117.19$8,859.23$113,976.42
80$105,520.99$8,491.26$114,012.25
81$105,634.22$8,130.07$113,764.29
82$106,364.89$8,089.98$114,454.87
83$106,721.64$8,259.44$114,981.08
84$106,997.03$8,194.59$115,191.62
85$107,087.45$8,769.53$115,856.98
86$107,357.24$9,030.17$116,387.41
87$102,800.99$8,748.70$111,549.69
88$103,072.99$8,140.25$111,213.24
89$103,599.42$8,152.25$111,751.67
90$104,160.27$8,929.53$113,089.80
91$103,971.89$8,282.87$112,254.76
92$104,216.40$8,362.99$112,579.39
93$104,731.66$8,559.90$113,291.56
94$105,503.99$7,933.19$113,437.18
95$105,651.06$8,144.50$113,795.56
96$105,869.68$9,302.47$115,172.15
97$106,422.62$8,566.71$114,989.33
98$106,629.15$9,045.12$115,674.27
99$106,870.06$9,778.79$116,648.85
100$107,106.32$9,513.90$116,620.22
101$107,678.72$9,271.62$116,950.34
102$108,449.56$9,077.42$117,526.98
103$108,959.93$8,546.02$117,505.95
104$108,877.13$8,367.84$117,244.97
105$109,273.07$8,671.12$117,944.19
106$109,768.00$9,162.09$118,930.09
107$110,015.36$8,530.11$118,545.47
108$110,320.25$8,379.28$118,699.53
109$110,814.17$8,754.22$119,568.39
110$111,122.29$9,098.45$120,220.74
111$111,508.41$9,582.40$121,090.81
112$111,900.14$9,274.06$121,174.20
113$112,283.83$8,832.87$121,116.70
114$112,109.39$8,711.82$120,821.21
115$112,566.19$9,354.42$121,920.61
116$113,212.17$9,337.32$122,549.49
117$114,057.99$9,235.32$123,293.31
118$109,597.89$8,288.82$117,886.71
119$109,660.64$8,416.98$118,077.62
120$109,991.94$9,333.44$119,325.38
121$110,931.65$9,836.88$120,768.53
122$111,466.28$9,482.51$120,948.79
123$111,776.62$9,311.96$121,088.58
124$112,037.53$9,380.50$121,418.03
125$112,205.24$9,124.88$121,330.12
126$112,530.45$9,172.14$121,702.59
127$112,868.66$9,515.79$122,384.45
128$113,022.18$9,379.49$122,401.67
129$114,244.61$8,772.23$123,016.84
130$114,514.38$8,897.97$123,412.35
131$114,831.63$8,618.64$123,450.27
132$115,203.32$7,961.27$123,164.59
133$115,735.34$7,984.00$123,719.34
134$115,987.59$8,432.58$124,420.17
135$116,213.52$8,335.66$124,549.18
136$116,438.17$8,294.95$124,733.12
137$116,769.10$7,069.45$123,838.55
138$116,885.50$8,470.21$125,355.71
139$117,396.07$8,003.14$125,399.21
140$117,423.91$7,747.63$125,171.54
141$117,255.17$7,608.07$124,863.24
142$117,756.10$9,225.02$126,981.12
143$117,974.22$10,138.86$128,113.08
144$118,105.78$9,721.74$127,827.52
145$118,505.19$9,432.20$127,937.39
146$119,292.96$9,326.10$128,619.06
147$119,598.08$9,280.47$128,878.55
148$120,390.86$9,014.57$129,405.43
149$115,643.72$8,792.59$124,436.31
150$116,045.36$10,283.88$126,329.24
151$116,545.31$10,286.27$126,831.58
152$116,750.08$10,244.63$126,994.71
153$117,293.16$10,156.14$127,449.30
154$117,866.45$9,475.29$127,341.74
155$118,416.27$9,422.08$127,838.35
156$118,903.77$9,503.39$128,407.16
157$119,255.03$9,660.24$128,915.27
158$119,663.39$9,325.00$128,988.39
159$120,203.90$8,284.72$128,488.62
160$120,351.83$8,676.89$129,028.72
161$120,607.26$9,785.38$130,392.64
162$121,216.57$10,064.53$131,281.10
163$121,787.44$9,506.47$131,293.91
164$122,250.55$8,859.73$131,110.28
165$122,524.26$8,461.13$130,985.39
166$122,519.48$8,235.89$130,755.37
167$122,997.70$8,558.16$131,555.86
168$123,045.89$9,006.08$132,051.97
169$123,261.92$9,194.22$132,456.14
170$123,754.92$9,356.35$133,111.27
171$124,223.33$9,136.72$133,360.05
172$124,370.24$8,861.33$133,231.57
173$124,856.35$9,560.88$134,417.23
174$125,579.20$9,810.87$135,390.07
175$125,519.84$9,116.08$134,635.92
176$125,570.18$8,921.49$134,491.67
177$120,752.43$9,889.67$130,642.10
178$121,196.19$10,381.61$131,577.80
179$122,269.65$9,946.10$132,215.75
180$122,666.00$9,782.36$132,448.36
181$122,953.80$9,212.69$132,166.49
182$123,135.58$9,243.68$132,379.26
183$123,560.82$9,154.56$132,715.38
184$123,550.39$8,738.62$132,289.01
185$124,112.27$8,778.95$132,891.22
186$124,393.03$9,347.49$133,740.52
187$124,571.50$9,699.63$134,271.13
188$124,854.87$9,669.00$134,523.87
189$125,097.97$9,390.77$134,488.74
190$125,191.84$9,634.96$134,826.80
191$125,532.55$9,960.39$135,492.94
192$125,958.38$10,027.03$135,985.41
193$126,651.19$9,567.81$136,219.00
194$126,982.09$9,699.15$136,681.24
195$127,618.25$9,204.48$136,822.73
196$128,650.97$8,275.97$136,926.94
197$128,916.96$8,674.12$137,591.08
198$129,105.45$8,597.91$137,703.36
199$129,817.84$7,842.87$137,660.71
200$129,987.84$8,171.32$138,159.16
201$129,967.19$8,337.44$138,304.63
202$129,965.84$8,236.67$138,202.51
203$130,437.86$8,440.00$138,877.86
204$130,838.24$8,752.65$139,590.89
205$130,501.22$8,554.25$139,055.47
206$130,562.62$8,857.56$139,420.18
207$130,907.86$9,363.04$140,270.90
208$126,052.98$9,575.65$135,628.63
209$126,359.36$10,030.23$136,389.59
210$126,513.26$9,995.85$136,509.11
211$126,722.88$10,034.92$136,757.80
212$126,811.89$10,939.92$137,751.81
213$127,643.01$10,448.94$138,091.95
214$128,026.94$9,740.54$137,767.48
215$128,055.55$9,655.63$137,711.18
216$128,515.19$9,845.46$138,360.65
217$128,503.35$10,051.39$138,554.74
218$128,791.65$9,843.53$138,635.18
219$128,914.29$10,428.69$139,342.98
220$129,173.65$10,688.85$139,862.50
221$129,861.51$9,870.13$139,731.64
222$130,610.37$9,734.48$140,344.85
223$130,262.24$10,011.44$140,273.68
224$130,572.36$10,179.35$140,751.71
225$130,905.01$10,615.94$141,520.95
226$131,294.38$10,919.60$142,213.98
227$131,552.24$10,783.74$142,335.98
228$131,702.52$10,884.46$142,586.98
229$132,129.28$10,970.51$143,099.79
230$132,817.50$10,845.05$143,662.55
231$132,730.22$10,799.23$143,529.45
232$133,070.70$10,865.12$143,935.82
233$133,504.13$10,655.21$144,159.34
234$133,721.51$10,944.93$144,666.44
235$133,950.53$11,295.59$145,246.12
236$134,386.62$11,194.96$145,581.58
237$134,815.83$11,097.64$145,913.47
238$130,130.25$11,499.90$141,630.15
239$130,777.73$10,719.13$141,496.86
240$131,265.96$10,081.36$141,347.32
241$132,099.57$9,894.98$141,994.55
242$132,350.16$10,011.83$142,361.99
243$132,548.51$9,809.20$142,357.71
244$132,725.67$9,613.27$142,338.94
245$132,856.81$10,373.92$143,230.73
246$132,861.18$10,227.05$143,088.23
247$133,008.73$10,258.76$143,267.49
248$133,448.56$11,232.25$144,680.81
249$133,710.57$11,044.44$144,755.01
250$134,135.43$10,978.31$145,113.74
251$134,550.55$10,988.93$145,539.48
252$134,554.59$11,069.88$145,624.47
253$134,753.72$11,077.14$145,830.86
254$134,922.46$10,706.78$145,629.24
255$135,320.78$11,055.54$146,376.32
256$135,750.34$11,666.99$147,417.33
257$136,043.71$11,476.73$147,520.44
258$136,272.97$11,207.73$147,480.70
259$137,084.20$10,567.22$147,651.42
260$137,544.34$10,405.85$147,950.19
261$137,774.37$10,533.04$148,307.41
262$138,098.89$11,161.13$149,260.02
263$138,345.81$10,508.48$148,854.29
264$138,565.83$10,313.80$148,879.63
265$139,028.99$11,124.63$150,153.62
266$139,338.29$10,762.82$150,101.11
267$140,277.75$10,989.59$151,267.34
268$140,012.99$11,734.50$151,747.49
269$134,960.80$11,489.62$146,450.42
270$135,180.33$11,207.54$146,387.87
271$135,425.29$10,976.57$146,401.86
272$135,671.86$11,174.82$146,846.68
273$136,245.09$11,168.16$147,413.25
274$136,865.88$10,678.30$147,544.18
275$136,961.42$10,769.53$147,730.95
276$137,015.85$11,508.38$148,524.23
277$137,578.05$11,193.73$148,771.78
278$138,157.89$10,802.22$148,960.11
279$138,402.47$11,060.48$149,462.95
280$138,894.44$11,136.87$150,031.31
281$139,416.01$11,030.23$150,446.24
282$139,759.80$10,596.07$150,355.87
283$139,960.92$10,185.74$150,146.66
284$140,112.91$10,377.63$150,490.54
285$140,433.97$10,656.52$151,090.49
286$140,682.35$10,177.02$150,859.37
287$140,628.86$10,305.50$150,934.36
288$141,184.19$11,008.93$152,193.12
289$141,309.49$11,381.34$152,690.83
290$141,418.33$10,740.08$152,158.41
291$141,527.01$10,933.05$152,460.06
292$141,925.79$11,372.63$153,298.42
293$142,114.01$11,230.79$153,344.80
294$142,489.68$11,301.85$153,791.53
295$142,626.34$11,522.51$154,148.85
296$142,089.70$11,685.72$153,775.42
297$142,581.24$12,209.18$154,790.42
298$143,163.86$12,829.29$155,993.15
299$138,496.02$12,097.51$150,593.53
300$138,612.43$12,188.95$150,801.38
301$138,964.42$12,342.49$151,306.91
302$139,407.67$12,367.11$151,774.78
303$139,467.99$12,412.66$151,880.65
304$139,850.09$12,655.42$152,505.51
305$140,193.53$12,988.00$153,181.53
306$140,435.65$12,915.95$153,351.60
307$140,709.39$12,838.00$153,547.39
308$141,322.67$12,036.33$153,359.00
309$141,535.91$11,806.18$153,342.09
310$141,736.72$12,467.77$154,204.49
311$142,175.69$12,642.61$154,818.30
312$142,438.99$12,528.81$154,967.80
313$142,874.51$12,271.90$155,146.41
314$143,018.49$12,637.55$155,656.04
315$143,122.62$13,012.98$156,135.60
316$143,684.16$12,461.14$156,145.30
317$144,067.62$12,174.28$156,241.90
318$144,792.30$11,700.62$156,492.92
319$145,101.62$11,616.23$156,717.85
320$145,411.55$11,939.65$157,351.20
321$145,447.00$11,685.35$157,132.35
322$146,016.27$11,493.98$157,510.25
323$146,473.04$12,109.53$158,582.57
324$146,490.02$12,375.27$158,865.29
325$146,997.10$12,395.97$159,393.07
326$147,241.12$12,419.03$159,660.15
327$147,557.26$12,427.92$159,985.18
328$147,805.42$12,555.73$160,361.15
329$148,208.62$12,394.33$160,602.95
330$143,382.04$12,383.24$155,765.28
331$143,510.57$12,438.84$155,949.41
332$144,008.27$12,284.47$156,292.74
333$144,282.07$11,706.51$155,988.58
334$144,657.96$11,553.15$156,211.11
335$144,990.60$12,060.00$157,050.60
336$145,662.12$11,374.87$157,036.99
337$146,246.32$11,590.17$157,836.49
338$146,363.91$11,735.16$158,099.07
339$146,366.14$11,557.33$157,923.47
340$146,823.68$11,269.25$158,092.93
341$147,090.86$12,053.89$159,144.75
342$147,121.17$11,973.93$159,095.10
343$147,350.08$11,607.33$158,957.41
344$147,463.80$11,848.04$159,311.84
345$147,544.29$12,020.78$159,565.07
346$147,976.13$12,305.63$160,281.76
347$148,846.08$12,281.29$161,127.37
348$149,327.76$12,071.76$161,399.52
349$149,503.26$12,356.20$161,859.46
350$149,956.62$11,941.02$161,897.64
351$149,975.21$12,002.40$161,977.61
352$150,131.25$11,933.33$162,064.58
353$150,878.45$12,221.31$163,099.76
354$151,924.71$11,406.13$163,330.84
355$151,866.18$10,865.02$162,731.20
356$152,393.98$11,340.01$163,733.99
357$152,784.49$11,861.84$164,646.33
358$153,159.17$11,481.92$164,641.09
359$153,426.25$11,394.59$164,820.84
360$155,151.64$11,237.81$166,389.45
361$151,187.84$11,256.66$162,444.50
362$152,710.80$10,790.50$163,501.30
363$154,307.47$10,125.81$164,433.28
364$156,090.67$9,107.24$165,197.91
365$156,949.92$8,691.58$165,641.50
Download all 365 days as CSV ↓

One simulated GPT-OSS plus planner run. The total-assets score excludes $666.67 in unpaid liabilities; it is not net profit.

Run details and verification

Seed 2301, 365 days completed. After an interruption at day 335, 670 saved responses were replayed to resume the same run. The complete annual offline replay audit passed; the market was not rerolled and outcomes were not selected.

725 model responses, 15,137 tool calls and 1 tool error. External inference API spend was $0; hardware and electricity costs were not measured.

Receivables: $0.00. Unpaid liabilities: $666.67. Net value after those adjustments: $164,974.83.

This is a single-seed synthetic-market baseline, not an average across runs, a model ranking or a real-world return forecast. The seed was used in earlier short trials, not a fresh held-out evaluation.

Download annual results and score definition ↗ · 2026-10-18 · LM Studio · MLX MXFP4

Earlier 30-day trial data ↗

INSIDE THE SIMULATION

A business to manage, every day.

01

Source & stock

Compare suppliers, buy singles and sealed products, and manage deliveries and inventory constraints.

02

Price & sell

Set prices, respond to customer demand and offers, and cover ongoing operating expenses.

03

Settle & measure

Add ending cash to the value of remaining inventory. Inventory uses simulated liquidation bids after selling costs.

Read the complete methodology →

From trajectories to stronger comparisons.

These results remain development experiments. Stronger comparisons need full-year runs from more models, matched seeds, and multiple market periods. Release-date trends and frontier-progress analyses also need verified release metadata and enough comparable results.

Future models should be compared with both local GPT-OSS plus planner and the planner alone under matching settings, then evaluated on newly reserved seeds. One annual run is not enough to establish a reliable model ranking.

PUT THE RESEARCH TO WORK

Explore the research tools.

Presentation inspired by Andon Labs’ Vending-Bench 2. TCG-Bench uses its own simulator, data, and scoring rules.

Data updated: 2026-10-18 · All amounts in USD