Claude Sonnet 5 vs Qwen3.8 Max Preview
Wins 1 of 8 areas
Long documents
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Following instructions
Qwen3.8 Max Preview is the stronger all-rounder.Claude Sonnet 5 is better at long documents.
Scores updated · 36 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.
- AgentsCarrying out multi-step tasks on its own04Qwen3.8 Max Preview4 of 4 tests
- CodingWriting and fixing software24Qwen3.8 Max Preview4 of 6 tests
- ReasoningHard problems that need careful thinking02Qwen3.8 Max Preview2 of 4 tests · 2 ties
- Images and chartsUnderstanding pictures, charts and video02Qwen3.8 Max Preview2 of 2 tests
- FactsGetting facts right instead of making them up12Qwen3.8 Max Preview2 of 3 tests
- MathCompetition and research-level math12Qwen3.8 Max Preview2 of 3 tests
- Following instructionsDoing exactly what it is asked01Qwen3.8 Max Preview1 of 1 test
- Long documentsFinding answers in very long texts10Claude Sonnet 51 of 1 test
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 33% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.8 Max Preview pulls ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+24.8points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+17points ahead
- Short factual questions, answered correctlySimpleQA Verified+13.6points ahead
Where Claude Sonnet 5 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+8.4points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+7.8points ahead
- Code for real scientific research problemsSciCode+2.2points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.8 Max Preview
- LMArena · WebDevQwen3.8 Max Preview by 131 rating points15411672+131 rating
- Terminal-Bench 2.1Qwen3.8 Max Preview by 8.380.588.8+8.3
- LiveBench · CodingClaude Sonnet 5 by 7.880.772.9+7.8
- LiveBench · Agentic CodingQwen3.8 Max Preview by 5.359.464.7+5.3
- SWE-bench ProQwen3.8 Max Preview by 4.563.267.7+4.5
- SciCodeClaude Sonnet 5 by 2.254.352.1+2.2
AgentsQwen3.8 Max Preview
- Terminal-Bench 4.0Qwen3.8 Max Preview by 24.814.138.9+24.8
- τ-Bench V3 · BankingQwen3.8 Max Preview by 10.537.347.8+10.5
- GDPValQwen3.8 Max Preview by 10.148.258.3+10.1
- OSWorld-VerifiedQwen3.8 Max Preview by 4.981.286.1+4.9
ReasoningQwen3.8 Max Preview
- Humanity's Last ExamQwen3.8 Max Preview by 1.841.343.1+1.8
- GPQA DiamondQwen3.8 Max Preview by 1.791.192.8+1.7
- CritPttie16.917.7tie
- LiveBench · Reasoningtie88.788.2tie
FactsQwen3.8 Max Preview
- SimpleQA VerifiedQwen3.8 Max Preview by 13.633.747.3+13.6
- AA-Omniscience · Non-hallucinationQwen3.8 Max Preview by 10.660.671.2+10.6
- AA-Omniscience · AccuracyClaude Sonnet 5 by 8.44031.7+8.4
Images and chartsQwen3.8 Max Preview
- MMMU-ProQwen3.8 Max Preview by 5.577.382.8+5.5
- LMArena · VisionQwen3.8 Max Preview by 40 rating points12741314+40 rating
MathQwen3.8 Max Preview
- FrontierMath Tier 4Qwen3.8 Max Preview by 1729.346.3+17
- FrontierMath Tiers 1-3 (v2)Qwen3.8 Max Preview by 9.165.674.7+9.1
- LiveBench · MathematicsClaude Sonnet 5 by 1.692.991.3+1.6
Following instructionsQwen3.8 Max Preview
- LiveBench · Instruction FollowingQwen3.8 Max Preview by 10.263.974.1+10.2
Other results12 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.
- ToolathlonQwen3.8 Max Preview by 18.254.372.5+18.2
- LVBenchQwen3.8 Max Preview by 13.368.581.8+13.3
- GDPval-AA v2Qwen3.8 Max Preview by 121 rating points16181739+121 rating
- AA IntelligenceQwen3.8 Max Preview by 7.238.245.4+7.2
- livebench_data_analysisQwen3.8 Max Preview by 6.771.778.4+6.7
- AA Agentic IndexQwen3.8 Max Preview by 5.344.349.6+5.3
- livebench_languageQwen3.8 Max Preview by 4.77579.7+4.7
- AA-OmniscienceClaude Sonnet 5 by 4.516.412+4.5
- DeepSWE 1.1Qwen3.8 Max Preview by 2.65456.6+2.6
- Toolathlon VerifiedClaude Sonnet 5 by 2.274.772.5+2.2
- HLE (with tools)Claude Sonnet 5 by 1.257.456.2+1.2
- Artificial Analysis Coding Indextie71.571.8tie
Questions people ask
Which is better, Claude Sonnet 5 or Qwen3.8 Max Preview?
Qwen3.8 Max Preview wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and following instructions. Claude Sonnet 5 wins long documents.
Which is better for coding?
Qwen3.8 Max Preview. It wins 4 of the 6 coding tests both models report; Claude Sonnet 5 wins 2.
Which is cheaper?
Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; Qwen3.8 Max Preview costs $2.00 and $6.00. That makes Qwen3.8 Max Preview about 33% cheaper for the same work.
How do you compare the two?
We use the 36 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 12 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.