GLM-5.2 wins more areas, narrowly.Qwen3.6 Plus is cheaper and better at facts.
Scores updated · 38 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 software70GLM-5.27 of 7 tests
- MathCompetition and research-level math50GLM-5.25 of 5 tests
- ReasoningHard problems that need careful thinking40GLM-5.24 of 4 tests
- AgentsCarrying out multi-step tasks on its own30GLM-5.23 of 3 tests
- FactsGetting facts right instead of making them up12Qwen3.6 Plus2 of 3 tests
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
- Following instructionsDoing exactly what it is asked11Even1 each
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.
Qwen3.6 Plus costs 40% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GLM-5.2 pulls ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+20.9points ahead
- Real work tasks from 44 professionsGDPVal+19points ahead
- Research-level physics problemsCritPt+18points ahead
Where Qwen3.6 Plus pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+9.9points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+2.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+1.9points ahead
Every test, side by side
All 38 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGLM-5.2
- Terminal-Bench 2.1GLM-5.2 by 16.577.961.4+16.5
- LMArena · WebDevGLM-5.2 by 142 rating points16031461+142 rating
- SciCodeGLM-5.2 by 10.551.240.7+10.5
- LiveBench · Agentic CodingGLM-5.2 by 10.451.841.4+10.4
- Terminal-Bench HardGLM-5.2 by 6.950.843.9+6.9
- SWE-bench ProGLM-5.2 by 5.562.156.6+5.5
- LiveBench · CodingGLM-5.2 by 1.579.778.2+1.5
AgentsGLM-5.2
- GDPValGLM-5.2 by 1943.724.7+19
- τ-Bench V3 · BankingGLM-5.2 by 13.834.620.8+13.8
- MCP AtlasGLM-5.2 by 2.776.874.1+2.7
ReasoningGLM-5.2
- CritPtGLM-5.2 by 1820.92.9+18
- Humanity's Last ExamGLM-5.2 by 13.341.127.8+13.3
- LiveBench · ReasoningGLM-5.2 by 2.878.675.8+2.8
- GPQA DiamondGLM-5.2 by 1.389.588.2+1.3
FactsQwen3.6 Plus
- SimpleQA VerifiedQwen3.6 Plus by 9.934.244.1+9.9
- AA-Omniscience · Non-hallucinationGLM-5.2 by 8.373.765.4+8.3
- AA-Omniscience · AccuracyQwen3.6 Plus by 2.124.326.4+2.1
MathGLM-5.2
- FrontierMath Tiers 1-3 (v2)GLM-5.2 by 20.959.238.3+20.9
- IMOAnswerBenchGLM-5.2 by 7.29183.8+7.2
- LiveBench · MathematicsGLM-5.2 by 6.189.883.7+6.1
- HMMT Feb. 2026GLM-5.2 by 4.792.587.8+4.7
- AIME 2026GLM-5.2 by 3.999.295.3+3.9
Following instructionsEven
- LiveBench · Instruction FollowingGLM-5.2 by 462.358.3+4
- IFBenchQwen3.6 Plus by 1.973.375.2+1.9
Other results13 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.
- Artificial Analysis Coding IndexGLM-5.2 by 14.368.854.5+14.3
- NL2RepoGLM-5.2 by 1148.937.9+11
- AA Agentic IndexGLM-5.2 by 10.439.429+10.4
- Tool-DecathlonGLM-5.2 by 8.448.239.8+8.4
- ToolathlonGLM-5.2 by 8.448.239.8+8.4
- AA IntelligenceGLM-5.2 by 6.733.727+6.7
- HLE (with tools)GLM-5.2 by 4.154.750.6+4.1
- livebench_data_analysisGLM-5.2 by 3.873.769.9+3.8
- AA-OmniscienceGLM-5.2 by 3.54.40.9+3.5
- τ²-Bench Telecom (AA run)GLM-5.2 by 1.499.197.7+1.4
- livebench_languageGLM-5.2 by 1.276.275+1.2
- HMMT 2025tie94.494.6tie
- HMMT Nov. 2025tie94.494.6tie
Questions people ask
Which is better, GLM-5.2 or Qwen3.6 Plus?
GLM-5.2 wins four of the seven areas where both have results: coding, agents, reasoning and math. Qwen3.6 Plus wins facts, and costs 40% less. They are level on long documents and following instructions.
Which is better for coding?
GLM-5.2. It wins 7 of the 7 coding tests both models report; Qwen3.6 Plus wins none.
Which is cheaper?
GLM-5.2 costs $1.40 per million input tokens and $4.40 per million output tokens; Qwen3.6 Plus costs $0.50 and $3.00. That makes Qwen3.6 Plus about 40% cheaper for the same work.
How do you compare the two?
We use the 38 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 13 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.