Claude Mythos 5 vs GPT-5.6 Sol
Wins 3 of 4 areas
Coding · Agents · Images and charts
Wins 1 of 4 areas
Reasoning
Claude Mythos 5 is the stronger all-rounder.GPT-5.6 Sol is cheaper and better at reasoning.
Scores updated · 21 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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.
- CodingWriting and fixing software10Claude Mythos 51 of 2 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own10Claude Mythos 51 of 1 test
- Images and chartsUnderstanding pictures, charts and video10Claude Mythos 51 of 1 test
- ReasoningHard problems that need careful thinking12GPT-5.6 Sol2 of 3 tests
Agents and images and charts rest on a single test each.
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.
GPT-5.6 Sol costs 60% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Mythos 5 pulls ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+15.4points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+8.3points ahead
- Reasoning about charts from research papersCharXiv (RQ)+3.1points ahead
Every test, side by side
All 21 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Mythos 5
- SWE-bench ProClaude Mythos 5 by 15.48064.6+15.4
- Terminal-Bench 2.1tie8888tie
ReasoningGPT-5.6 Sol
- Humanity's Last ExamClaude Mythos 5 by 8.357.849.5+8.3
- CritPtGPT-5.6 Sol by 3.728.632.3+3.7
- ARC-AGI-2GPT-5.6 Sol by 3.389.292.5+3.3
Images and chartsClaude Mythos 5
- CharXiv (RQ)Claude Mythos 5 by 3.188.985.8+3.1
Other results14 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.
- Program BenchClaude Mythos 5 by 61.386.325+61.3
- GDP (Surge AI)Claude Mythos 5 by 56.687.330.7+56.6
- OSWorld 2.0 (partial)Claude Mythos 5 by 10.372.962.6+10.3
- ProteinGym HardClaude Mythos 5 by 10.345.835.5+10.3
- HealthBenchClaude Mythos 5 by 5.762.757+5.7
- Terminal-Bench 4.0Claude Mythos 5 by 4.74237.3+4.7
- Toolathlon VerifiedClaude Mythos 5 by 4.479.374.9+4.4
- OfficeQA ProClaude Mythos 5 by 3.967.163.2+3.9
- ToolathlonClaude Mythos 5 by 3.161.158+3.1
- HealthBench ProfessionalClaude Mythos 5 by 2.863.360.5+2.8
- Terminal-Bench-Science 0.1Claude Mythos 5 by 2.324.722.4+2.3
- ARC-AGI-1Claude Mythos 5 by 298.596.5+2
- GDPval-AA v2Claude Mythos 5 by 12 rating points17231711+12 rating
- HLE (with tools)tie63.864.5tie
Questions people ask
Which is better, Claude Mythos 5 or GPT-5.6 Sol?
Claude Mythos 5 wins three of the four areas where both have results: coding, agents and images and charts. GPT-5.6 Sol wins reasoning, and costs 60% less.
Which is better for coding?
Claude Mythos 5. It wins 1 of the 2 coding tests both models report; GPT-5.6 Sol wins none, and 1 is a tie.
Which is cheaper?
Claude Mythos 5 costs $10.00 per million input tokens and $50.00 per million output tokens; GPT-5.6 Sol costs $4.00 and $20.00. That makes GPT-5.6 Sol about 60% cheaper for the same work.
How do you compare the two?
We use the 21 benchmark tests both models have published scores on. The verdict counts the 7 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.