Head-to-head comparison across 3benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Claude Sonnet 4.6
83
GPT-5.4 mini
71
Pick Claude Sonnet 4.6 if you want the stronger benchmark profile. GPT-5.4 mini only becomes the better choice if agentic is the priority or you want the cheaper token bill.
Agentic
+0.5 difference
Knowledge
+16.3 difference
Multimodal
+0.8 difference
Claude Sonnet 4.6
GPT-5.4 mini
$3 / $15
$0.75 / $4.5
44 t/s
201 t/s
1.48s
3.85s
200K
400K
Pick Claude Sonnet 4.6 if you want the stronger benchmark profile. GPT-5.4 mini only becomes the better choice if agentic is the priority or you want the cheaper token bill.
Claude Sonnet 4.6 is clearly ahead on the provisional aggregate, 83 to 71. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Sonnet 4.6's sharpest advantage is in knowledge, where it averages 73.7 against 57.4. The single biggest benchmark swing on the page is HLE, 49% to 41.5%. GPT-5.4 mini does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
Claude Sonnet 4.6 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $0.75 input / $4.50 output per 1M tokens for GPT-5.4 mini. That is roughly 3.3x on output cost alone. GPT-5.4 mini is the reasoning model in the pair, while Claude Sonnet 4.6 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. GPT-5.4 mini gives you the larger context window at 400K, compared with 200K for Claude Sonnet 4.6.
Claude Sonnet 4.6 is ahead on BenchLM's provisional leaderboard, 83 to 71. The biggest single separator in this matchup is HLE, where the scores are 49% and 41.5%.
Claude Sonnet 4.6 has the edge for knowledge tasks in this comparison, averaging 73.7 versus 57.4. Inside this category, HLE is the benchmark that creates the most daylight between them.
GPT-5.4 mini has the edge for agentic tasks in this comparison, averaging 65.6 versus 65.1. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Claude Sonnet 4.6 has the edge for multimodal and grounded tasks in this comparison, averaging 77.4 versus 76.6. GPT-5.4 mini stays close enough that the answer can still flip depending on your workload.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.