Claude Opus 4.8 vs Claude Sonnet 4.5
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
Claude Opus 4.8 is the stronger all-rounder.Claude Sonnet 4.5 is cheaper.
Scores updated · 42 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 own60Claude Opus 4.86 of 6 tests
- ReasoningHard problems that need careful thinking50Claude Opus 4.85 of 5 tests
- FactsGetting facts right instead of making them up30Claude Opus 4.83 of 3 tests
- MathCompetition and research-level math30Claude Opus 4.83 of 3 tests
- Images and chartsUnderstanding pictures, charts and video10Claude Opus 4.81 of 1 test
- Long documentsFinding answers in very long texts10Claude Opus 4.81 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Opus 4.81 of 1 test
Images and charts, 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.
Claude Sonnet 4.5 costs 40% 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
- Finds hard-to-locate facts by browsing the webBrowseComp+60.2points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+58.5points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+56.1points ahead
Where Claude Sonnet 4.5 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 42 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.8
- Terminal-Bench 2.1Claude Opus 4.8 by 28.884.655.8+28.8
- SWE-bench ProClaude Opus 4.8 by 25.669.243.6+25.6
- Terminal-Bench HardClaude Opus 4.8 by 22.758.335.6+22.7
- SWE-bench MultilingualClaude Opus 4.8 by 17.484.467+17.4
- LMArena · WebDevClaude Opus 4.8 by 162 rating points15561394+162 rating
- SWE-bench VerifiedClaude Opus 4.8 by 11.488.677.2+11.4
- SciCodeClaude Opus 4.8 by 8.754.445.7+8.7
AgentsClaude Opus 4.8
- BrowseCompClaude Opus 4.8 by 60.284.324.1+60.2
- MCP AtlasClaude Opus 4.8 by 38.482.243.8+38.4
- GDPValClaude Opus 4.8 by 27.347.820.5+27.3
- OSWorld-VerifiedClaude Opus 4.8 by 2283.461.4+22
- Terminal-Bench 4.0Claude Opus 4.8 by 21.721.70+21.7
- τ-Bench V3 · BankingClaude Opus 4.8 by 9.734.224.5+9.7
ReasoningClaude Opus 4.8
- ARC-AGI-2Claude Opus 4.8 by 58.572.113.6+58.5
- Humanity's Last ExamClaude Opus 4.8 by 30.948.717.8+30.9
- CritPtClaude Opus 4.8 by 19.820.91.1+19.8
- SimpleBenchClaude Opus 4.8 by 10.564.854.3+10.5
- GPQA DiamondClaude Opus 4.8 by 8.69283.4+8.6
FactsClaude Opus 4.8
- SimpleQA VerifiedClaude Opus 4.8 by 22.35330.7+22.3
- AA-Omniscience · AccuracyClaude Opus 4.8 by 15.948.832.9+15.9
- AA-Omniscience · Non-hallucinationClaude Opus 4.8 by 9.860.750.9+9.8
Images and chartsClaude Opus 4.8
- CharXiv (RQ)Claude Opus 4.8 by 22.789.967.2+22.7
MathClaude Opus 4.8
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.8 by 56.18023.9+56.1
- FrontierMath Tier 4Claude Opus 4.8 by 53.756.12.4+53.7
- IMOAnswerBenchClaude Opus 4.8 by 17.683.565.9+17.6
Following instructionsClaude Opus 4.8
- IFBenchClaude Opus 4.8 by 4.962.257.3+4.9
Other results15 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 28.928.8-0.1+28.9
- ARC-AGI-1Claude Opus 4.8 by 28.892.563.7+28.8
- frontiermath_tier_4_v1Claude Opus 4.8 by 27.131.34.2+27.1
- HLE (with tools)Claude Opus 4.8 by 25.957.932+25.9
- AA Agentic IndexClaude Opus 4.8 by 25.142.617.5+25.1
- Terminal-Bench 2.0Claude Opus 4.8 by 24.674.650+24.6
- Artificial Analysis Coding IndexClaude Opus 4.8 by 22.274.352.1+22.2
- AA IntelligenceClaude Opus 4.8 by 21.141.820.7+21.1
- Toolathlon Pass@∞Claude Opus 4.8 by 19.448.128.7+19.4
- ToolathlonClaude Opus 4.8 by 18.959.941+18.9
- τ²-Bench Telecom (AA run)Claude Opus 4.8 by 16.394.478.1+16.3
- HealthBenchClaude Opus 4.8 by 15.159.344.2+15.1
- HMMT Nov. 2025Claude Opus 4.8 by 14.896.581.7+14.8
- Toolathlon Avg turnsClaude Sonnet 4.5 by 7.524.532+7.5
- matharena_visual_math_overallClaude Opus 4.8 by 5.881.675.8+5.8
Questions people ask
Which is better, Claude Opus 4.8 or Claude Sonnet 4.5?
Claude Opus 4.8 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Claude Sonnet 4.5 wins none, but costs 40% less.
Which is better for coding?
Claude Opus 4.8. It wins 7 of the 7 coding tests both models report; Claude Sonnet 4.5 wins none.
Which is cheaper?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Sonnet 4.5 costs $3.00 and $15.00. That makes Claude Sonnet 4.5 about 40% cheaper for the same work.
How do you compare the two?
We use the 42 benchmark tests both models have published scores on. The verdict counts the 27 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.