Claude Sonnet 4.6 vs Qwen3.8 Max Preview
Wins 0 of 8 areas
—
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Following instructions
Qwen3.8 Max Preview is the stronger all-rounder.
Scores updated · 35 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 own05Qwen3.8 Max Preview5 of 6 tests · 1 tie
- CodingWriting and fixing software15Qwen3.8 Max Preview5 of 6 tests
- ReasoningHard problems that need careful thinking04Qwen3.8 Max Preview4 of 4 tests
- Images and chartsUnderstanding pictures, charts and video02Qwen3.8 Max Preview2 of 2 tests
- Following instructionsDoing exactly what it is asked02Qwen3.8 Max Preview2 of 2 tests
- FactsGetting facts right instead of making them up12Qwen3.8 Max Preview2 of 3 tests
- MathCompetition and research-level math01Qwen3.8 Max Preview1 of 1 test
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Math and long documents 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 56% 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 Qwen3.8 Max Preview pulls ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+35.9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+26.2points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+22.1points ahead
Where Claude Sonnet 4.6 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+9.2points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+6.4points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.8 Max Preview
- LiveBench · Agentic CodingQwen3.8 Max Preview by 22.142.664.7+22.1
- Terminal-Bench 2.1Qwen3.8 Max Preview by 17.671.288.8+17.6
- LMArena · WebDevQwen3.8 Max Preview by 149 rating points15231672+149 rating
- SWE-bench ProQwen3.8 Max Preview by 9.658.167.7+9.6
- LiveBench · CodingClaude Sonnet 4.6 by 6.479.372.9+6.4
- SciCodeQwen3.8 Max Preview by 250.152.1+2
AgentsQwen3.8 Max Preview
- Terminal-Bench 4.0Qwen3.8 Max Preview by 35.9338.9+35.9
- GDPValQwen3.8 Max Preview by 21.736.658.3+21.7
- AA ApexAgentsQwen3.8 Max Preview by 14.42842.4+14.4
- OSWorld-VerifiedQwen3.8 Max Preview by 13.672.586.1+13.6
- τ-Bench V3 · BankingQwen3.8 Max Preview by 13.434.447.8+13.4
- AA IT-Bench SREtie39.840.3tie
ReasoningQwen3.8 Max Preview
- CritPtQwen3.8 Max Preview by 14.63.117.7+14.6
- Humanity's Last ExamQwen3.8 Max Preview by 9.533.643.1+9.5
- GPQA DiamondQwen3.8 Max Preview by 5.387.592.8+5.3
- LiveBench · ReasoningQwen3.8 Max Preview by 3.484.888.2+3.4
FactsQwen3.8 Max Preview
- AA-Omniscience · Non-hallucinationQwen3.8 Max Preview by 19.651.671.2+19.6
- SimpleQA VerifiedQwen3.8 Max Preview by 14.532.847.3+14.5
- AA-Omniscience · AccuracyClaude Sonnet 4.6 by 9.240.931.7+9.2
Images and chartsQwen3.8 Max Preview
- MMMU-ProQwen3.8 Max Preview by 9.573.382.8+9.5
- LMArena · VisionQwen3.8 Max Preview by 32 rating points12821314+32 rating
Following instructionsQwen3.8 Max Preview
- IFBenchQwen3.8 Max Preview by 26.256.682.8+26.2
- LiveBench · Instruction FollowingQwen3.8 Max Preview by 10.963.274.1+10.9
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.
- GDPval-AA v2Qwen3.8 Max Preview by 344 rating points13951739+344 rating
- ToolathlonQwen3.8 Max Preview by 31.54172.5+31.5
- DeepSWE 1.1Qwen3.8 Max Preview by 26.63056.6+26.6
- AA Agentic IndexQwen3.8 Max Preview by 16.533.149.6+16.5
- AA IntelligenceQwen3.8 Max Preview by 15.330.145.4+15.3
- HLE (with tools)Qwen3.8 Max Preview by 9.446.856.2+9.4
- Artificial Analysis Coding IndexQwen3.8 Max Preview by 8.86371.8+8.8
- livebench_languageQwen3.8 Max Preview by 3.676.179.7+3.6
- livebench_data_analysistie7878.4tie
- AA-Omnisciencetie12.212tie
Questions people ask
Which is better, Claude Sonnet 4.6 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 4.6 wins none. They are level on long documents.
Which is better for coding?
Qwen3.8 Max Preview. It wins 5 of the 6 coding tests both models report; Claude Sonnet 4.6 wins 1.
Which is cheaper?
Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; Qwen3.8 Max Preview costs $2.00 and $6.00. That makes Qwen3.8 Max Preview about 56% cheaper for the same work.
How do you compare the two?
We use the 35 benchmark tests both models have published scores on. The verdict counts the 25 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.