GPT-5.6 Sol is the stronger all-rounder.Hy4 is cheaper and better at coding.
Scores updated · 17 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.
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.
Hy4 costs 86% 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 GPT-5.6 Sol pulls ahead
- Research-level physics problemsCritPt+15.4points ahead
- Long professional tasks in banking, consulting and lawAA ApexAgents+2.8points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+2.6points ahead
Where Hy4 pulls ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+1.1points ahead
Every test, side by side
All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingHy4
- Terminal-Bench 2.1GPT-5.6 Sol by 2.68885.4+2.6
- LMArena · WebDevHy4 by 15 rating points16161631+15 rating
- SWE-bench ProHy4 by 1.164.665.7+1.1
AgentsGPT-5.6 Sol
- AA ApexAgentsGPT-5.6 Sol by 2.839.937.1+2.8
- MCP Atlastie83.683.7tie
ReasoningGPT-5.6 Sol
- CritPtGPT-5.6 Sol by 15.432.316.9+15.4
- GPQA DiamondGPT-5.6 Sol by 1.894.192.3+1.8
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.
- Agents' Last ExamGPT-5.6 Sol by 29.952.722.8+29.9
- JobBenchHy4 by 16.345.461.7+16.3
- ToolathlonHy4 by 16.15874.1+16.1
- SWE-MarathonGPT-5.6 Sol by 10.642.531.9+10.6
- MathArena Apex (Pass@1)Hy4 by 8.665.674.2+8.6
- DeepSWEGPT-5.6 Sol by 8.472.764.3+8.4
- CyberGymGPT-5.6 Sol by 6.184.578.4+6.1
- Program BenchGPT-5.6 Sol by 5.52317.5+5.5
- OfficeQA ProHy4 by 363.266.2+3
- PostTrainBenchtie36.235.6tie
Questions people ask
Which is better, GPT-5.6 Sol or Hy4?
GPT-5.6 Sol wins two of the three areas where both have results: agents and reasoning. Hy4 wins coding, and costs 86% less.
Which is better for coding?
Hy4. It wins 2 of the 3 coding tests both models report; GPT-5.6 Sol wins 1.
Which is cheaper?
GPT-5.6 Sol costs $4.00 per million input tokens and $20.00 per million output tokens; Hy4 costs $0.83 and $2.50. That makes Hy4 about 86% cheaper for the same work.
How do you compare the two?
We use the 17 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 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.