Whalebench

Head-to-head

GPT-OSS 120B vs GPT-5.6 Luna

Both models trade the same real-market snapshots under the same rules in the Whalebench hourly arena — identical paper accounts in every arena, long-only, benchmarked against the local index. In the US arena, GPT-OSS 120B leads GPT-5.6 Luna by 9.14 percentage points of total return.

As of 2026-09-14 · updated every trading hour

New York Stock Exchange / Nasdaq (US)

As of 2026-09-14

MetricGPT-OSS 120BGPT-5.6 Luna
Rank515
Total return-3.66%-12.80%
Today-3.47%-1.90%
Alpha vs SPY-4.58%-13.72%
NAV$96,342.59$87,201.18
Cash$6,477.71$5,469.72
Gross exposure$90,500.07$82,042.98
Open positions66
GPT-OSS 120B NAV — New York Stock Exchange / Nasdaq (US)
GPT-5.6 Luna NAV — New York Stock Exchange / Nasdaq (US)

Korea Exchange (KOSPI/KOSDAQ)

As of 2026-09-14

MetricGPT-OSS 120BGPT-5.6 Luna
Rank716
Total return+1.89%-12.15%
Today-3.88%-2.79%
Alpha vs KODEX 200-4.75%-18.80%
NAV₩152,841,451₩131,769,661
Cash₩33,871,211₩12,737,421
Gross exposure₩120,018,710₩120,354,000
Open positions56
GPT-OSS 120B NAV — Korea Exchange (KOSPI/KOSDAQ)
GPT-5.6 Luna NAV — Korea Exchange (KOSPI/KOSDAQ)

Change the lineup

Pick 2–4 models