Claude Mythos Preview is the stronger all-rounder.
Scores updated · 15 tests both models report · How we compare
Where each one wins
Tests won in each of the three areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Coding rests on a single test.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Mythos Preview pulls ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+19.2points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+18.9points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+2.5points ahead
Where GPT-5.5 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Mythos Preview
- SWE-bench ProClaude Mythos Preview by 19.277.858.6+19.2
AgentsClaude Mythos Preview
- BrowseCompClaude Mythos Preview by 2.586.984.4+2.5
- OSWorld-Verifiedtie79.678.7tie
ReasoningClaude Mythos Preview
- Humanity's Last ExamClaude Mythos Preview by 18.964.745.8+18.9
- GPQA DiamondClaude Mythos Preview by 1.194.693.5+1.1
Other results10 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- GraphWalks Parents 1M subsetClaude Mythos Preview by 3795.558.5+37
- GraphWalks BFS 1M subsetClaude Mythos Preview by 28.974.345.4+28.9
- HealthBench ProfessionalClaude Mythos Preview by 12.964.751.8+12.9
- HLE (with tools)Claude Mythos Preview by 12.564.752.2+12.5
- GraphWalks BFS 256KClaude Mythos Preview by 1285.773.7+12
- GraphWalks — Parents task, 256K-token context subsetClaude Mythos Preview by 9.899.990.1+9.8
- HealthBenchClaude Mythos Preview by 4.661.156.5+4.6
- BrowseComp (single-agent)Claude Mythos Preview by 3.587.984.4+3.5
- CyberGymClaude Mythos Preview by 1.383.181.8+1.3
- Terminal-Bench 2.0tie8282.7tie
Questions people ask
Which is better, Claude Mythos Preview or GPT-5.5?
Claude Mythos Preview wins all three areas where both have results: coding, agents and reasoning. GPT-5.5 wins none.
Which is better for coding?
Claude Mythos Preview. It wins the one coding test both models report.
How do you compare the two?
We use the 15 benchmark tests both models have published scores on. The verdict counts the 5 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.