Claude Opus 5 vs Qwen3.8 Max Preview
Wins 5 of 8 areas
Coding · Reasoning · Facts · Images and charts · Math
Wins 2 of 8 areas
Long documents · Following instructions
Claude Opus 5 is the stronger all-rounder.Qwen3.8 Max Preview is cheaper and better at long documents.
Both rank among the ten best models we track in agents.
Scores updated · 37 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 software40Claude Opus 54 of 6 tests · 2 ties
- ReasoningHard problems that need careful thinking30Claude Opus 53 of 4 tests · 1 tie
- MathCompetition and research-level math30Claude Opus 53 of 3 tests
- FactsGetting facts right instead of making them up21Claude Opus 52 of 3 tests
- Images and chartsUnderstanding pictures, charts and video10Claude Opus 51 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Qwen3.8 Max Preview1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.8 Max Preview1 of 1 test
- AgentsCarrying out multi-step tasks on its own22Even2 each
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.
Qwen3.8 Max Preview costs 73% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Opus 5 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+29.2points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+26.9points ahead
- Short factual questions, answered correctlySimpleQA Verified+12.6points ahead
Where Qwen3.8 Max Preview pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+32points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+10.3points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+5.7points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 5
- SWE-bench ProClaude Opus 5 by 11.579.267.7+11.5
- LiveBench · CodingClaude Opus 5 by 8.681.572.9+8.6
- SciCodeClaude Opus 5 by 4.356.452.1+4.3
- LMArena · WebDevClaude Opus 5 by 18 rating points16901672+18 rating
- LiveBench · Agentic Codingtie65.264.7tie
- Terminal-Bench 2.1tie89.188.8tie
AgentsEven
- Terminal-Bench 4.0Claude Opus 5 by 10.14938.9+10.1
- τ-Bench V3 · BankingQwen3.8 Max Preview by 5.742.147.8+5.7
- GDPValClaude Opus 5 by 2.861.158.3+2.8
- OSWorld-VerifiedQwen3.8 Max Preview by 2.783.486.1+2.7
ReasoningClaude Opus 5
- Humanity's Last ExamClaude Opus 5 by 11.854.943.1+11.8
- CritPtClaude Opus 5 by 11.429.117.7+11.4
- LiveBench · ReasoningClaude Opus 5 by 391.288.2+3
- GPQA Diamondtie93.292.8tie
FactsClaude Opus 5
- AA-Omniscience · Non-hallucinationQwen3.8 Max Preview by 3239.271.2+32
- AA-Omniscience · AccuracyClaude Opus 5 by 29.260.931.7+29.2
- SimpleQA VerifiedClaude Opus 5 by 12.659.947.3+12.6
Images and chartsClaude Opus 5
- MMMU-ProClaude Opus 5 by 1.984.782.8+1.9
- LMArena · Visiontie13191314tie
MathClaude Opus 5
- FrontierMath Tier 4Claude Opus 5 by 26.973.246.3+26.9
- FrontierMath Tiers 1-3 (v2)Claude Opus 5 by 10.985.674.7+10.9
- LiveBench · MathematicsClaude Opus 5 by 4.495.791.3+4.4
Long documentsQwen3.8 Max Preview
- AA-LCRQwen3.8 Max Preview by 179.380.3+1
Following instructionsQwen3.8 Max Preview
- LiveBench · Instruction FollowingQwen3.8 Max Preview by 10.363.874.1+10.3
Other results13 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 5 by 25.137.112+25.1
- Agents' Last ExamQwen3.8 Max Preview by 20.831.652.4+20.8
- JobBenchClaude Opus 5 by 12.365.753.4+12.3
- DeepSWE 1.1Claude Opus 5 by 12.268.856.6+12.2
- livebench_languageClaude Opus 5 by 988.779.7+9
- GDPval-AA v2Claude Opus 5 by 85 rating points18241739+85 rating
- Toolathlon VerifiedClaude Opus 5 by 8.180.672.5+8.1
- HLE (with tools)Claude Opus 5 by 7.463.656.2+7.4
- AA Agentic IndexClaude Opus 5 by 6.656.249.6+6.6
- LVBenchQwen3.8 Max Preview by 6.475.481.8+6.4
- Artificial Analysis Coding IndexClaude Opus 5 by 6.27871.8+6.2
- AA IntelligenceClaude Opus 5 by 5.450.845.4+5.4
- livebench_data_analysisQwen3.8 Max Preview by 3.874.578.4+3.8
Questions people ask
Which is better, Claude Opus 5 or Qwen3.8 Max Preview?
Claude Opus 5 wins five of the eight areas we test: coding, reasoning, facts, images and charts and math. Qwen3.8 Max Preview wins long documents and following instructions, and costs 73% less. They are level on agents.
Which is better for coding?
Claude Opus 5. It wins 4 of the 6 coding tests both models report; Qwen3.8 Max Preview wins none, and 2 are ties.
Which is cheaper?
Claude Opus 5 costs $5.00 per million input tokens and $25.00 per million output tokens; Qwen3.8 Max Preview costs $2.00 and $6.00. That makes Qwen3.8 Max Preview about 73% cheaper for the same work.
How do you compare the two?
We use the 37 benchmark tests both models have published scores on. The verdict counts the 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.