Head-to-head comparison across 4benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Claude Mythos 5
99
Claude Opus 4.7 (Adaptive)
84
Verified leaderboard positions: Claude Mythos 5 #1 · Claude Opus 4.7 (Adaptive) #9
Pick Claude Mythos 5 if you want the stronger benchmark profile. Claude Opus 4.7 (Adaptive) only becomes the better choice if you want the cheaper token bill.
Agentic
+12.1 difference
Coding
+13.0 difference
Knowledge
+6.4 difference
Multimodal
+28.4 difference
Claude Mythos 5
Claude Opus 4.7 (Adaptive)
$10 / $50
$5 / $25
N/A
N/A
N/A
N/A
1M+
1M
Pick Claude Mythos 5 if you want the stronger benchmark profile. Claude Opus 4.7 (Adaptive) only becomes the better choice if you want the cheaper token bill.
Claude Mythos 5 is clearly ahead on the provisional aggregate, 99 to 84. 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 multimodal & grounded, where it averages 92.7 against 64.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 88% to 69.4%.
Claude Mythos 5 is also the more expensive model on tokens at $10.00 input / $50.00 output per 1M tokens, versus $5.00 input / $25.00 output per 1M tokens for Claude Opus 4.7 (Adaptive). That is roughly 2.0x on output cost alone. Claude Mythos 5 gives you the larger context window at 1M+, compared with 1M for Claude Opus 4.7 (Adaptive).
Claude Mythos 5 is ahead on BenchLM's provisional leaderboard, 99 to 84. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 88% and 69.4%.
Claude Mythos 5 has the edge for knowledge tasks in this comparison, averaging 74.6 versus 68.2. Inside this category, HLE w/o tools is the benchmark that creates the most daylight between them.
Claude Mythos 5 has the edge for coding in this comparison, averaging 85.9 versus 72.9. Inside this category, Terminal-Bench 2.0 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 74.9. 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 64.3. Inside this category, CharXiv w/o tools 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.