GLM-5.2 vs Qwen3.5 397B A17B
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Long documents
Wins 1 of 7 areas
Following instructions
GLM-5.2 is the stronger all-rounder.Qwen3.5 397B A17B is cheaper and better at following instructions.
Scores updated · 37 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 software50GLM-5.25 of 5 tests
- AgentsCarrying out multi-step tasks on its own50GLM-5.25 of 5 tests
- MathCompetition and research-level math40GLM-5.24 of 4 tests
- ReasoningHard problems that need careful thinking20GLM-5.22 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up21GLM-5.22 of 3 tests
- Long documentsFinding answers in very long texts10GLM-5.21 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.5 397B A17B1 of 1 test
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.
Qwen3.5 397B A17B costs 28% 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 GLM-5.2 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+62.6points ahead
- Real work tasks from 44 professionsGDPVal+28.9points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+28points ahead
Where Qwen3.5 397B A17B pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.5points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+5.5points ahead
Every test, side by side
All 37 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 26.677.951.3+26.6
- LMArena · WebDevGLM-5.2 by 203 rating points16031400+203 rating
- SWE-bench ProGLM-5.2 by 11.262.150.9+11.2
- Terminal-Bench HardGLM-5.2 by 9.950.840.9+9.9
- SciCodeGLM-5.2 by 6.451.244.8+6.4
AgentsGLM-5.2
- GDPValGLM-5.2 by 28.943.714.8+28.9
- τ-Bench V3 · BankingGLM-5.2 by 21.234.613.4+21.2
- AA ApexAgentsGLM-5.2 by 18.433.715.3+18.4
- AA IT-Bench SREGLM-5.2 by 8.642.734.1+8.6
- Terminal-Bench 4.0GLM-5.2 by 110+1
ReasoningGLM-5.2
- CritPtGLM-5.2 by 19.220.91.7+19.2
- Humanity's Last ExamGLM-5.2 by 12.141.129+12.1
- GPQA Diamondtie89.589.3tie
FactsGLM-5.2
- AA-Omniscience · Non-hallucinationGLM-5.2 by 62.673.711.1+62.6
- SimpleQA VerifiedGLM-5.2 by 8.234.226+8.2
- AA-Omniscience · AccuracyQwen3.5 397B A17B by 6.524.330.8+6.5
MathGLM-5.2
- FrontierMath Tiers 1-3 (v2)GLM-5.2 by 2859.231.2+28
- IMOAnswerBenchGLM-5.2 by 10.19180.9+10.1
- AIME 2026GLM-5.2 by 7.999.291.3+7.9
- HMMT Feb. 2026GLM-5.2 by 4.692.587.9+4.6
Following instructionsQwen3.5 397B A17B
- IFBenchQwen3.5 397B A17B by 5.573.378.8+5.5
Other results15 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.
- GDPval-AA v2GLM-5.2 by 546 rating points1508962+546 rating
- AA-OmniscienceGLM-5.2 by 35.14.4-30.8+35.1
- AA Agentic IndexGLM-5.2 by 28.839.410.6+28.8
- Artificial Analysis Coding IndexGLM-5.2 by 20.668.848.2+20.6
- Toolathlon VerifiedGLM-5.2 by 19.259.940.7+19.2
- NL2RepoGLM-5.2 by 16.748.932.2+16.7
- AA IntelligenceGLM-5.2 by 15.333.718.4+15.3
- τ³-Bench BankingGLM-5.2 by 13.426.813.4+13.4
- SWEBench Pro PublicGLM-5.2 by 11.262.150.9+11.2
- ToolathlonGLM-5.2 by 9.948.238.3+9.9
- HLE (with tools)GLM-5.2 by 6.454.748.3+6.4
- τ²-Bench Telecom (AA run)GLM-5.2 by 3.599.195.6+3.5
- HMMT 2025GLM-5.2 by 1.794.492.7+1.7
- HMMT Nov. 2025GLM-5.2 by 1.794.492.7+1.7
- StrongREJECTtie98.599.4tie
Questions people ask
Which is better, GLM-5.2 or Qwen3.5 397B A17B?
GLM-5.2 wins six of the seven areas where both have results: coding, agents, reasoning, facts, math and long documents. Qwen3.5 397B A17B wins following instructions, and costs 28% less.
Which is better for coding?
GLM-5.2. It wins 5 of the 5 coding tests both models report; Qwen3.5 397B A17B wins none.
Which is cheaper?
GLM-5.2 costs $1.40 per million input tokens and $4.40 per million output tokens; Qwen3.5 397B A17B costs $0.60 and $3.60. That makes Qwen3.5 397B A17B about 28% cheaper for the same work.
How do you compare the two?
We use the 37 benchmark tests both models have published scores on. The verdict counts the 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.