Head-to-head comparison across 3benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Claude Mythos Preview
99
GPT-5.4 Pro
92
Verified leaderboard positions: Claude Mythos Preview #1 · GPT-5.4 Pro unranked
Pick Claude Mythos Preview if you want the stronger benchmark profile. GPT-5.4 Pro only becomes the better choice if agentic is the priority or you need the larger 1.05M context window.
Agentic
+6.9 difference
Knowledge
+25.9 difference
Multimodal
+1.3 difference
Claude Mythos Preview
GPT-5.4 Pro
$25 / $125
$30 / $180
N/A
74 t/s
N/A
151.79s
1M
1.05M
Pick Claude Mythos Preview if you want the stronger benchmark profile. GPT-5.4 Pro only becomes the better choice if agentic is the priority or you need the larger 1.05M context window.
Claude Mythos Preview is clearly ahead on the provisional aggregate, 99 to 92. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Mythos Preview's sharpest advantage is in knowledge, where it averages 74.9 against 49. The single biggest benchmark swing on the page is HLE w/o tools, 56.8% to 42.7%. GPT-5.4 Pro does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
GPT-5.4 Pro is also the more expensive model on tokens at $30.00 input / $180.00 output per 1M tokens, versus $25.00 input / $125.00 output per 1M tokens for Claude Mythos Preview. GPT-5.4 Pro gives you the larger context window at 1.05M, compared with 1M for Claude Mythos Preview.
Claude Mythos Preview is ahead on BenchLM's provisional leaderboard, 99 to 92. The biggest single separator in this matchup is HLE w/o tools, where the scores are 56.8% and 42.7%.
Claude Mythos Preview has the edge for knowledge tasks in this comparison, averaging 74.9 versus 49. Inside this category, HLE w/o tools is the benchmark that creates the most daylight between them.
GPT-5.4 Pro has the edge for agentic tasks in this comparison, averaging 89.3 versus 82.4. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
GPT-5.4 Pro has the edge for multimodal and grounded tasks in this comparison, averaging 94 versus 92.7. 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.