Claude Opus 4.8 vs Hy3-preview
Wins 5 of 7 areas
Coding · Agents · Reasoning · Facts · Following instructions
Wins 2 of 7 areas
Math · Long documents
Claude Opus 4.8 is the stronger all-rounder.Hy3-preview is cheaper and better at math.
Scores updated · 31 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 software70Claude Opus 4.87 of 7 tests
- AgentsCarrying out multi-step tasks on its own50Claude Opus 4.85 of 6 tests · 1 tie
- ReasoningHard problems that need careful thinking30Claude Opus 4.83 of 3 tests
- FactsGetting facts right instead of making them up20Claude Opus 4.82 of 2 tests
- Following instructionsDoing exactly what it is asked10Claude Opus 4.81 of 1 test
- MathCompetition and research-level math01Hy3-preview1 of 1 test
- Long documentsFinding answers in very long texts01Hy3-preview1 of 1 test
Math, long documents and following instructions 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.
Hy3-preview costs 98% 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 Opus 4.8 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+34.8points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+26.5points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+21.2points ahead
Where Hy3-preview pulls ahead
- Olympiad math problems with short answersIMOAnswerBench+6.5points ahead
- Reasons across sets of long documentsAA-LCR+1.3points ahead
Every test, side by side
All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.8
- Terminal-Bench HardClaude Opus 4.8 by 26.558.331.8+26.5
- Terminal-Bench 2.1Claude Opus 4.8 by 20.284.664.4+20.2
- SWE-bench ProClaude Opus 4.8 by 11.369.257.9+11.3
- SWE-bench VerifiedClaude Opus 4.8 by 10.688.678+10.6
- SWE-bench MultilingualClaude Opus 4.8 by 8.684.475.8+8.6
- SciCodeClaude Opus 4.8 by 5.854.448.6+5.8
- LMArena · WebDevClaude Opus 4.8 by 48 rating points15561508+48 rating
AgentsClaude Opus 4.8
- Terminal-Bench 4.0Claude Opus 4.8 by 21.221.70.5+21.2
- GDPValClaude Opus 4.8 by 19.547.828.3+19.5
- AA ApexAgentsClaude Opus 4.8 by 13.839.425.6+13.8
- τ-Bench V3 · BankingClaude Opus 4.8 by 11.334.222.9+11.3
- MCP AtlasClaude Opus 4.8 by 3.182.279.1+3.1
- BrowseComptie84.384.2tie
ReasoningClaude Opus 4.8
- CritPtClaude Opus 4.8 by 1620.94.9+16
- Humanity's Last ExamClaude Opus 4.8 by 15.248.733.5+15.2
- GPQA DiamondClaude Opus 4.8 by 2.39289.7+2.3
FactsClaude Opus 4.8
- AA-Omniscience · Non-hallucinationClaude Opus 4.8 by 34.860.725.9+34.8
- AA-Omniscience · AccuracyClaude Opus 4.8 by 16.848.832+16.8
Following instructionsClaude Opus 4.8
- IFBenchClaude Opus 4.8 by 14.262.248+14.2
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.
- AA-OmniscienceClaude Opus 4.8 by 47.328.8-18.5+47.3
- DeepSWEClaude Opus 4.8 by 305828+30
- τ²-Bench Telecom (AA run)Claude Opus 4.8 by 26.994.467.5+26.9
- NL2RepoClaude Opus 4.8 by 24.169.745.6+24.1
- AA Agentic IndexClaude Opus 4.8 by 1742.625.6+17
- AA IntelligenceClaude Opus 4.8 by 16.541.825.3+16.5
- Artificial Analysis Coding IndexClaude Opus 4.8 by 15.574.358.8+15.5
- ToolathlonClaude Opus 4.8 by 11.459.948.5+11.4
- WideSearchHy3-preview by 3.572.976.4+3.5
- DeepSearchQA (F1)Claude Opus 4.8 by 2.193.191+2.1
Questions people ask
Which is better, Claude Opus 4.8 or Hy3-preview?
Claude Opus 4.8 wins five of the seven areas where both have results: coding, agents, reasoning, facts and following instructions. Hy3-preview wins math and long documents, and costs 98% less.
Which is better for coding?
Claude Opus 4.8. It wins 7 of the 7 coding tests both models report; Hy3-preview wins none.
Which is cheaper?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Hy3-preview costs $0.14 and $0.56. That makes Hy3-preview about 98% cheaper for the same work.
How do you compare the two?
We use the 31 benchmark tests both models have published scores on. The verdict counts the 21 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.