Head-to-head comparison across 2benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
DeepSeek V4 Pro
70
Step 3.7 Flash
72
Verified leaderboard positions: DeepSeek V4 Pro #26 · Step 3.7 Flash unranked
Pick Step 3.7 Flash if you want the stronger benchmark profile. DeepSeek V4 Pro only becomes the better choice if coding is the priority or you need the larger 1M context window.
Agentic
+6.8 difference
Coding
+2.5 difference
DeepSeek V4 Pro
Step 3.7 Flash
$1.74 / $3.48
$0.2 / $1.15
N/A
N/A
N/A
N/A
1M
256K
Pick Step 3.7 Flash if you want the stronger benchmark profile. DeepSeek V4 Pro only becomes the better choice if coding is the priority or you need the larger 1M context window.
Step 3.7 Flash has the cleaner provisional overall profile here, landing at 72 versus 70. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Step 3.7 Flash's sharpest advantage is in agentic, where it averages 65.9 against 59.1. The single biggest benchmark swing on the page is SWE-bench Pro, 52.1% to 56.3%. DeepSeek V4 Pro does hit back in coding, so the answer changes if that is the part of the workload you care about most.
DeepSeek V4 Pro is also the more expensive model on tokens at $1.74 input / $3.48 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. That is roughly 3.0x on output cost alone. Step 3.7 Flash is the reasoning model in the pair, while DeepSeek V4 Pro is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. DeepSeek V4 Pro gives you the larger context window at 1M, compared with 256K for Step 3.7 Flash.
Step 3.7 Flash is ahead on BenchLM's provisional leaderboard, 72 to 70. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 52.1% and 56.3%.
DeepSeek V4 Pro has the edge for coding in this comparison, averaging 58.8 versus 56.3. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 65.9 versus 59.1. Inside this category, Claw-Eval 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.