GPT-5.2 vs Qwen3.7 Max
Wins 2 of 7 areas
Math · Long documents
Wins 4 of 7 areas
Coding · Reasoning · Facts · Following instructions
Qwen3.7 Max wins more areas, narrowly.GPT-5.2 is better at math.
Scores updated · 42 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.
- ReasoningHard problems that need careful thinking04Qwen3.7 Max4 of 5 tests · 1 tie
- Following instructionsDoing exactly what it is asked02Qwen3.7 Max2 of 2 tests
- CodingWriting and fixing software34Qwen3.7 Max4 of 8 tests · 1 tie
- FactsGetting facts right instead of making them up12Qwen3.7 Max2 of 3 tests
- MathCompetition and research-level math32GPT-5.23 of 6 tests · 1 tie
- Long documentsFinding answers in very long texts10GPT-5.21 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each · 1 tie
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 37% 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+55.6points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+30.7points ahead
- Common-sense trick questionsSimpleBench+24.6points ahead
Where GPT-5.2 pulls ahead
- Real work tasks from 44 professionsGDPVal+16.7points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+13.2points ahead
- Fresh competition math problemsLiveBench · Mathematics+7.9points ahead
Every test, side by side
All 42 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.7 Max
- SWE-bench ProQwen3.7 Max by 30.729.960.6+30.7
- SWE-bench MultilingualQwen3.7 Max by 11.666.778.3+11.6
- LMArena · WebDevQwen3.7 Max by 100 rating points14151515+100 rating
- LiveBench · Agentic CodingGPT-5.2 by 6.750.343.6+6.7
- Terminal-Bench HardQwen3.7 Max by 3.84750.8+3.8
- SciCodeGPT-5.2 by 2.652.149.5+2.6
- LiveBench · CodingGPT-5.2 by 1.976.174.2+1.9
- SWE-bench Verifiedtie8080.4tie
AgentsEven
- GDPValGPT-5.2 by 16.748.331.6+16.7
- MCP AtlasQwen3.7 Max by 15.860.676.4+15.8
- τ-Bench V3 · Bankingtie11.111.8tie
ReasoningQwen3.7 Max
- SimpleBenchQwen3.7 Max by 24.645.870.4+24.6
- Humanity's Last ExamQwen3.7 Max by 2.837.740.5+2.8
- GPQA DiamondQwen3.7 Max by 290.392.3+2
- CritPtQwen3.7 Max by 1.811.613.4+1.8
- LiveBench · Reasoningtie83.283.3tie
FactsQwen3.7 Max
- AA-Omniscience · Non-hallucinationQwen3.7 Max by 55.618.874.4+55.6
- SimpleQA VerifiedQwen3.7 Max by 18.737.155.8+18.7
- AA-Omniscience · AccuracyGPT-5.2 by 13.244.331.1+13.2
MathGPT-5.2
- LiveBench · MathematicsGPT-5.2 by 7.993.285.3+7.9
- IMOAnswerBenchQwen3.7 Max by 3.786.390+3.7
- FrontierMath Tiers 1-3 (v2)GPT-5.2 by 2.867.464.6+2.8
- FrontierMath Tier 4Qwen3.7 Max by 2.531.734.1+2.5
- AIME 2026GPT-5.2 by 1.398.397+1.3
- HMMT Feb. 2026tie9797.1tie
Following instructionsQwen3.7 Max
- LiveBench · Instruction FollowingQwen3.7 Max by 12.261.874+12.2
- IFBenchQwen3.7 Max by 5.175.480.5+5.1
Other results14 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 IndexGPT-5.2 by 36.360.223.9+36.3
- Artificial Analysis Coding IndexQwen3.7 Max by 17.348.766+17.3
- Terminal-Bench 2.0Qwen3.7 Max by 15.75469.7+15.7
- AA-OmniscienceQwen3.7 Max by 14.4-0.913.5+14.4
- τ²-Bench Telecom (AA run)Qwen3.7 Max by 9.984.894.7+9.9
- HLE (with tools)Qwen3.7 Max by 845.553.5+8
- livebench_data_analysisGPT-5.2 by 6.478.271.8+6.4
- MMLU-ProQwen3.7 Max by 2.986.789.6+2.9
- PaperBenchQwen3.7 Max by 1.163.764.8+1.1
- AA Intelligencetie30.429.5tie
- HMMT Nov. 2025tie95.895tie
- MMMLUtie89.690.3tie
- LiveBenchtie74.874.3tie
- livebench_languagetie79.879.7tie
Questions people ask
Which is better, GPT-5.2 or Qwen3.7 Max?
Qwen3.7 Max wins four of the seven areas where both have results: coding, reasoning, facts and following instructions. GPT-5.2 wins math and long documents. They are level on agents.
Which is better for coding?
Qwen3.7 Max. It wins 4 of the 8 coding tests both models report; GPT-5.2 wins 3, and 1 is a tie.
Which is cheaper?
GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; Qwen3.7 Max costs $2.50 and $7.50. That makes Qwen3.7 Max about 37% cheaper for the same work.
How do you compare the two?
We use the 42 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 14 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.