GLM-5.2 vs Step 3.7 Flash
Wins 6 of 7 areas
Coding · Agents · Reasoning · Math · Long documents · Following instructions
Wins 0 of 7 areas
—
GLM-5.2 is the stronger all-rounder.Step 3.7 Flash is cheaper.
Scores updated · 22 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 software40GLM-5.24 of 4 tests
- AgentsCarrying out multi-step tasks on its own40GLM-5.24 of 4 tests
- ReasoningHard problems that need careful thinking30GLM-5.23 of 3 tests
- MathCompetition and research-level math20GLM-5.22 of 2 tests
- Long documentsFinding answers in very long texts10GLM-5.21 of 1 test
- Following instructionsDoing exactly what it is asked10GLM-5.21 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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.
Step 3.7 Flash costs 77% 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+58.7points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+38.6points ahead
- Real work tasks from 44 professionsGDPVal+25.7points ahead
Where Step 3.7 Flash pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+1.5points ahead
Every test, side by side
All 22 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 38.677.939.3+38.6
- Terminal-Bench HardGLM-5.2 by 15.250.835.6+15.2
- SciCodeGLM-5.2 by 7.351.243.9+7.3
- SWE-bench ProGLM-5.2 by 5.862.156.3+5.8
AgentsGLM-5.2
- GDPValGLM-5.2 by 25.743.718+25.7
- τ-Bench V3 · BankingGLM-5.2 by 22.634.612+22.6
- AA ApexAgentsGLM-5.2 by 18.933.714.8+18.9
- AA IT-Bench SREGLM-5.2 by 12.442.730.3+12.4
ReasoningGLM-5.2
- Humanity's Last ExamGLM-5.2 by 19.741.121.4+19.7
- CritPtGLM-5.2 by 18.620.92.3+18.6
- GPQA DiamondGLM-5.2 by 8.689.580.9+8.6
FactsEven
- AA-Omniscience · Non-hallucinationGLM-5.2 by 58.773.715+58.7
- AA-Omniscience · AccuracyStep 3.7 Flash by 1.524.325.8+1.5
MathGLM-5.2
- HMMT Feb. 2026GLM-5.2 by 4.692.587.9+4.6
- AIME 2026GLM-5.2 by 4.299.295+4.2
Other results5 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-OmniscienceGLM-5.2 by 41.74.4-37.3+41.7
- Artificial Analysis Coding IndexGLM-5.2 by 29.268.839.6+29.2
- AA Agentic IndexGLM-5.2 by 17.739.421.7+17.7
- AA IntelligenceGLM-5.2 by 14.233.719.5+14.2
- τ²-Bench Telecom (AA run)tie99.198.5tie
Questions people ask
Which is better, GLM-5.2 or Step 3.7 Flash?
GLM-5.2 wins six of the seven areas where both have results: coding, agents, reasoning, math, long documents and following instructions. Step 3.7 Flash wins none, but costs 77% less. They are level on facts.
Which is better for coding?
GLM-5.2. It wins 4 of the 4 coding tests both models report; Step 3.7 Flash wins none.
Which is cheaper?
GLM-5.2 costs $1.40 per million input tokens and $4.40 per million output tokens; Step 3.7 Flash costs $0.20 and $1.15. That makes Step 3.7 Flash about 77% cheaper for the same work.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 17 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 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.