Claude Opus 4.6 vs Qwen3.7 Max
Wins 1 of 7 areas
Coding
Wins 4 of 7 areas
Reasoning · Facts · Long documents · Following instructions
Qwen3.7 Max wins more areas, narrowly.Claude Opus 4.6 is better at coding.
Scores updated · 44 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.
- Following instructionsDoing exactly what it is asked02Qwen3.7 Max2 of 2 tests
- ReasoningHard problems that need careful thinking12Qwen3.7 Max2 of 5 tests · 2 ties
- FactsGetting facts right instead of making them up12Qwen3.7 Max2 of 3 tests
- Long documentsFinding answers in very long texts01Qwen3.7 Max1 of 1 test
- CodingWriting and fixing software43Claude Opus 4.64 of 9 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own11Even1 each
- MathCompetition and research-level math22Even2 each · 2 ties
Long documents rests on a single test.
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 67% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.7 Max pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+37.2points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+27.4points ahead
- Olympiad math problems with short answersIMOAnswerBench+14.7points ahead
Where Claude Opus 4.6 pulls ahead
- Real work tasks from 44 professionsGDPVal+24.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+15.9points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+5.4points ahead
Every test, side by side
All 44 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.6
- SWE-bench ProQwen3.7 Max by 7.253.460.6+7.2
- LiveBench · Agentic CodingClaude Opus 4.6 by 5.44943.6+5.4
- Terminal-Bench HardQwen3.7 Max by 4.646.250.8+4.6
- LiveBench · CodingClaude Opus 4.6 by 478.274.2+4
- LMArena · WebDevClaude Opus 4.6 by 31 rating points15461515+31 rating
- LiveCodeBench v6Qwen3.7 Max by 2.888.891.6+2.8
- SciCodeClaude Opus 4.6 by 2.451.949.5+2.4
- SWE-bench Multilingualtie77.878.3tie
- SWE-bench Verifiedtie80.880.4tie
AgentsEven
ReasoningQwen3.7 Max
- LiveBench · ReasoningClaude Opus 4.6 by 5.488.783.3+5.4
- SimpleBenchQwen3.7 Max by 2.867.670.4+2.8
- GPQA DiamondQwen3.7 Max by 2.789.692.3+2.7
- CritPttie12.613.4tie
- Humanity's Last Examtie39.940.5tie
FactsQwen3.7 Max
- AA-Omniscience · Non-hallucinationQwen3.7 Max by 37.237.274.4+37.2
- AA-Omniscience · AccuracyClaude Opus 4.6 by 15.94731.1+15.9
- SimpleQA VerifiedQwen3.7 Max by 8.84755.8+8.8
MathEven
- IMOAnswerBenchQwen3.7 Max by 14.775.390+14.7
- FrontierMath Tier 4Qwen3.7 Max by 7.426.834.1+7.4
- LiveBench · MathematicsClaude Opus 4.6 by 489.385.3+4
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.6 by 1.46664.6+1.4
- HMMT Feb. 2026tie96.297.1tie
- AIME 2026tie96.797tie
Following instructionsQwen3.7 Max
- IFBenchQwen3.7 Max by 27.453.180.5+27.4
- LiveBench · Instruction FollowingQwen3.7 Max by 10.763.374+10.7
Other results16 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 IndexClaude Opus 4.6 by 43.767.623.9+43.7
- Artificial Analysis Coding IndexQwen3.7 Max by 17.948.166+17.9
- JobBenchClaude Opus 4.6 by 5.336.631.3+5.3
- Terminal-Bench 2.0Qwen3.7 Max by 4.365.469.7+4.3
- MCPMarkQwen3.7 Max by 4.156.760.8+4.1
- livebench_languageClaude Opus 4.6 by 3.683.379.7+3.6
- NL2RepoClaude Opus 4.6 by 2.649.847.2+2.6
- τ²-Bench Telecom (AA run)Qwen3.7 Max by 2.692.194.7+2.6
- AA IntelligenceClaude Opus 4.6 by 2.431.929.5+2.4
- LiveBenchClaude Opus 4.6 by 276.374.3+2
- livebench_data_analysisQwen3.7 Max by 1.969.971.8+1.9
- HMMT Nov. 2025Claude Opus 4.6 by 1.396.395+1.3
- MMMLUtie91.190.3tie
- MMLU-Protie89.189.6tie
- AA-Omnisciencetie13.713.5tie
- HLE (with tools)tie53.353.5tie
Questions people ask
Which is better, Claude Opus 4.6 or Qwen3.7 Max?
Qwen3.7 Max wins four of the seven areas where both have results: reasoning, facts, long documents and following instructions. Claude Opus 4.6 wins coding. They are level on agents and math.
Which is better for coding?
Claude Opus 4.6. It wins 4 of the 9 coding tests both models report; Qwen3.7 Max wins 3, and 2 are ties.
Which is cheaper?
Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; Qwen3.7 Max costs $2.50 and $7.50. That makes Qwen3.7 Max about 67% cheaper for the same work.
How do you compare the two?
We use the 44 benchmark tests both models have published scores on. The verdict counts the 28 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.