Head-to-head comparison across 2benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
GPT-5.3 Codex
86
Step 3.7 Flash
72
Pick GPT-5.3 Codex if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if you want the cheaper token bill.
Agentic
+5.6 difference
Coding
+6.8 difference
GPT-5.3 Codex
Step 3.7 Flash
$1.75 / $14
$0.2 / $1.15
79 t/s
N/A
88.26s
N/A
400K
256K
Pick GPT-5.3 Codex if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if you want the cheaper token bill.
GPT-5.3 Codex is clearly ahead on the provisional aggregate, 86 to 72. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.3 Codex's sharpest advantage is in coding, where it averages 63.1 against 56.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 77.3% to 59.5%.
GPT-5.3 Codex is also the more expensive model on tokens at $1.75 input / $14.00 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. That is roughly 12.2x on output cost alone. GPT-5.3 Codex gives you the larger context window at 400K, compared with 256K for Step 3.7 Flash.
GPT-5.3 Codex is ahead on BenchLM's provisional leaderboard, 86 to 72. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 77.3% and 59.5%.
GPT-5.3 Codex has the edge for coding in this comparison, averaging 63.1 versus 56.3. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
GPT-5.3 Codex has the edge for agentic tasks in this comparison, averaging 71.5 versus 65.9. Inside this category, Terminal-Bench 2.0 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.