Head-to-head comparison across 3benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Claude Mythos 5
99
GPT-5.4 mini
69
Verified leaderboard positions: Claude Mythos 5 #1 · GPT-5.4 mini unranked
Pick Claude Mythos 5 if you want the stronger benchmark profile. GPT-5.4 mini only becomes the better choice if you want the cheaper token bill.
Agentic
+21.4 difference
Knowledge
+17.2 difference
Multimodal
+16.1 difference
Claude Mythos 5
GPT-5.4 mini
$10 / $50
$0.75 / $4.5
N/A
201 t/s
N/A
3.85s
1M+
400K
Pick Claude Mythos 5 if you want the stronger benchmark profile. GPT-5.4 mini only becomes the better choice if you want the cheaper token bill.
Claude Mythos 5 is clearly ahead on the provisional aggregate, 99 to 69. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Mythos 5's sharpest advantage is in agentic, where it averages 87 against 65.6. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 88% to 60%.
Claude Mythos 5 is also the more expensive model on tokens at $10.00 input / $50.00 output per 1M tokens, versus $0.75 input / $4.50 output per 1M tokens for GPT-5.4 mini. That is roughly 11.1x on output cost alone. Claude Mythos 5 gives you the larger context window at 1M+, compared with 400K for GPT-5.4 mini.
Claude Mythos 5 is ahead on BenchLM's provisional leaderboard, 99 to 69. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 88% and 60%.
Claude Mythos 5 has the edge for knowledge tasks in this comparison, averaging 74.6 versus 57.4. Inside this category, HLE w/o tools is the benchmark that creates the most daylight between them.
Claude Mythos 5 has the edge for agentic tasks in this comparison, averaging 87 versus 65.6. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.
Claude Mythos 5 has the edge for multimodal and grounded tasks in this comparison, averaging 92.7 versus 76.6. Inside this category, MMMU-Pro 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.