Claude Sonnet 5 vs Qwen3.7 Max
Wins 4 of 7 areas
Coding · Agents · Math · Long documents
Wins 2 of 7 areas
Facts · Following instructions
Claude Sonnet 5 wins more areas, narrowly.Qwen3.7 Max is cheaper and better at facts.
Scores updated · 34 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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.
- CodingWriting and fixing software70Claude Sonnet 57 of 8 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own30Claude Sonnet 53 of 3 tests
- MathCompetition and research-level math21Claude Sonnet 52 of 3 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 51 of 1 test
- FactsGetting facts right instead of making them up12Qwen3.7 Max2 of 3 tests
- Following instructionsDoing exactly what it is asked01Qwen3.7 Max1 of 1 test
- ReasoningHard problems that need careful thinking22Even2 each · 1 tie
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.
Qwen3.7 Max costs 17% 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 Sonnet 5 pulls ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+25.5points ahead
- Real work tasks from 44 professionsGDPVal+16.7points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+15.8points ahead
Where Qwen3.7 Max pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+22.1points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+13.8points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+10.1points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 5
- LiveBench · Agentic CodingClaude Sonnet 5 by 15.859.443.6+15.8
- LiveBench · CodingClaude Sonnet 5 by 6.580.774.2+6.5
- Terminal-Bench 2.1Claude Sonnet 5 by 680.574.5+6
- SciCodeClaude Sonnet 5 by 4.854.349.5+4.8
- SWE-bench VerifiedClaude Sonnet 5 by 4.885.280.4+4.8
- SWE-bench ProClaude Sonnet 5 by 2.663.260.6+2.6
- LMArena · WebDevClaude Sonnet 5 by 24 rating points15391515+24 rating
- SWE-bench Multilingualtie78.378.3tie
AgentsClaude Sonnet 5
- τ-Bench V3 · BankingClaude Sonnet 5 by 25.537.311.8+25.5
- GDPValClaude Sonnet 5 by 16.748.331.6+16.7
- Terminal-Bench 4.0Claude Sonnet 5 by 12.614.11.5+12.6
ReasoningEven
- SimpleBenchQwen3.7 Max by 9.860.670.4+9.8
- LiveBench · ReasoningClaude Sonnet 5 by 5.488.783.3+5.4
- CritPtClaude Sonnet 5 by 3.516.913.4+3.5
- GPQA DiamondQwen3.7 Max by 1.291.192.3+1.2
- Humanity's Last Examtie41.340.5tie
FactsQwen3.7 Max
- SimpleQA VerifiedQwen3.7 Max by 22.133.755.8+22.1
- AA-Omniscience · Non-hallucinationQwen3.7 Max by 13.860.674.4+13.8
- AA-Omniscience · AccuracyClaude Sonnet 5 by 94031.1+9
MathClaude Sonnet 5
- LiveBench · MathematicsClaude Sonnet 5 by 7.692.985.3+7.6
- FrontierMath Tier 4Qwen3.7 Max by 4.929.334.1+4.9
- FrontierMath Tiers 1-3 (v2)Claude Sonnet 5 by 165.664.6+1
Following instructionsQwen3.7 Max
- LiveBench · Instruction FollowingQwen3.7 Max by 10.163.974+10.1
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.
- DeepSWE 1.1Claude Sonnet 5 by 32.45421.6+32.4
- Toolathlon VerifiedClaude Sonnet 5 by 2574.749.7+25
- AA Agentic IndexClaude Sonnet 5 by 20.444.323.9+20.4
- Terminal-Bench 2.0Claude Sonnet 5 by 10.780.469.7+10.7
- AA IntelligenceClaude Sonnet 5 by 8.738.229.5+8.7
- Artificial Analysis Coding IndexClaude Sonnet 5 by 5.571.566+5.5
- livebench_languageQwen3.7 Max by 4.77579.7+4.7
- HLE (with tools)Claude Sonnet 5 by 3.957.453.5+3.9
- AA-OmniscienceClaude Sonnet 5 by 316.413.5+3
- livebench_data_analysistie71.771.8tie
Questions people ask
Which is better, Claude Sonnet 5 or Qwen3.7 Max?
Claude Sonnet 5 wins four of the seven areas where both have results: coding, agents, math and long documents. Qwen3.7 Max wins facts and following instructions, and costs 17% less. They are level on reasoning.
Which is better for coding?
Claude Sonnet 5. It wins 7 of the 8 coding tests both models report; Qwen3.7 Max wins none, and 1 is a tie.
Which is cheaper?
Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; Qwen3.7 Max costs $2.50 and $7.50. That makes Qwen3.7 Max about 17% cheaper for the same work.
How do you compare the two?
We use the 34 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 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.