Claude Sonnet 4.5 vs Qwen3.6 Max Preview
Wins 0 of 6 areas
—
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Qwen3.6 Max Preview is the stronger all-rounder.
Scores updated · 19 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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.
- ReasoningHard problems that need careful thinking04Qwen3.6 Max Preview4 of 4 tests
- CodingWriting and fixing software03Qwen3.6 Max Preview3 of 3 tests
- FactsGetting facts right instead of making them up03Qwen3.6 Max Preview3 of 3 tests
- AgentsCarrying out multi-step tasks on its own01Qwen3.6 Max Preview1 of 1 test
- Long documentsFinding answers in very long texts01Qwen3.6 Max Preview1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.6 Max Preview1 of 1 test
Agents, 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.
Qwen3.6 Max Preview costs 49% 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 Qwen3.6 Max Preview pulls ahead
- Real work tasks from 44 professionsGDPVal+29.7points ahead
- Short factual questions, answered correctlySimpleQA Verified+21.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+19.3points ahead
Where Claude Sonnet 4.5 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.6 Max Preview
- LMArena · WebDevQwen3.6 Max Preview by 89 rating points13931482+89 rating
- Terminal-Bench HardQwen3.6 Max Preview by 8.335.643.9+8.3
- SciCodeQwen3.6 Max Preview by 1.245.746.9+1.2
ReasoningQwen3.6 Max Preview
- Humanity's Last ExamQwen3.6 Max Preview by 1317.830.8+13
- SimpleBenchQwen3.6 Max Preview by 8.754.363+8.7
- GPQA DiamondQwen3.6 Max Preview by 5.483.488.8+5.4
- CritPtQwen3.6 Max Preview by 2.61.13.7+2.6
FactsQwen3.6 Max Preview
- SimpleQA VerifiedQwen3.6 Max Preview by 21.330.752+21.3
- AA-Omniscience · AccuracyQwen3.6 Max Preview by 532.937.9+5
- AA-Omniscience · Non-hallucinationQwen3.6 Max Preview by 2.950.953.8+2.9
Long documentsQwen3.6 Max Preview
- AA-LCRQwen3.6 Max Preview by 8.472.380.7+8.4
Following instructionsQwen3.6 Max Preview
- IFBenchQwen3.6 Max Preview by 19.357.376.6+19.3
Other results6 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 Agentic IndexQwen3.6 Max Preview by 47.317.564.8+47.3
- τ²-Bench Telecom (AA run)Qwen3.6 Max Preview by 17.878.195.9+17.8
- AA-OmniscienceQwen3.6 Max Preview by 9.3-0.19.2+9.3
- AA IntelligenceQwen3.6 Max Preview by 7.720.728.4+7.7
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 7.252.144.9+7.2
- frontiermath_tier_4_v1tie4.24.2tie
Questions people ask
Which is better, Claude Sonnet 4.5 or Qwen3.6 Max Preview?
Qwen3.6 Max Preview wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. Claude Sonnet 4.5 wins none.
Which is better for coding?
Qwen3.6 Max Preview. It wins 3 of the 3 coding tests both models report; Claude Sonnet 4.5 wins none.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Qwen3.6 Max Preview costs $1.30 and $7.80. That makes Qwen3.6 Max Preview about 49% cheaper for the same work.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 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.