Head-to-head comparison across 2benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
GPT-5.4
89
Step 3.7 Flash
72
Verified leaderboard positions: GPT-5.4 #16 · Step 3.7 Flash unranked
Pick GPT-5.4 if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if you want the cheaper token bill.
Agentic
+11.1 difference
Coding
+1.4 difference
GPT-5.4
Step 3.7 Flash
$2.5 / $15
$0.2 / $1.15
74 t/s
N/A
151.79s
N/A
1.05M
256K
Pick GPT-5.4 if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if you want the cheaper token bill.
GPT-5.4 is clearly ahead on the provisional aggregate, 89 to 72. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.4's sharpest advantage is in agentic, where it averages 77 against 65.9. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 75.1% to 59.5%.
GPT-5.4 is also the more expensive model on tokens at $2.50 input / $15.00 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. That is roughly 13.0x on output cost alone. GPT-5.4 gives you the larger context window at 1.05M, compared with 256K for Step 3.7 Flash.
GPT-5.4 is ahead on BenchLM's provisional leaderboard, 89 to 72. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 75.1% and 59.5%.
GPT-5.4 has the edge for coding in this comparison, averaging 57.7 versus 56.3. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
GPT-5.4 has the edge for agentic tasks in this comparison, averaging 77 versus 65.9. Inside this category, DeepSearchQA is the benchmark that creates the most daylight between them.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.