The two are evenly matched.Claude Opus 4.6 is better at reasoning and facts; GLM-5.2 at coding and math.
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.
- CodingWriting and fixing software05GLM-5.25 of 6 tests · 1 tie
- MathCompetition and research-level math23GLM-5.23 of 6 tests · 1 tie
- ReasoningHard problems that need careful thinking32Claude Opus 4.63 of 6 tests · 1 tie
- FactsGetting facts right instead of making them up21Claude Opus 4.62 of 3 tests
- AgentsCarrying out multi-step tasks on its own11Even1 each · 1 tie
- 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.
GLM-5.2 costs 81% 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
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+36.5points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+20.2points ahead
- Olympiad math problems with short answersIMOAnswerBench+15.7points ahead
Where Claude Opus 4.6 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+46points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+22.7points ahead
- Short factual questions, answered correctlySimpleQA Verified+12.8points 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.
CodingGLM-5.2
- SWE-bench ProGLM-5.2 by 8.753.462.1+8.7
- LMArena · WebDevGLM-5.2 by 59 rating points15461605+59 rating
- Terminal-Bench HardGLM-5.2 by 4.646.250.8+4.6
- LiveBench · Agentic CodingGLM-5.2 by 2.84951.8+2.8
- LiveBench · CodingGLM-5.2 by 1.578.279.7+1.5
- SciCodetie51.951.2tie
AgentsEven
- MCP AtlasGLM-5.2 by 14.162.776.8+14.1
- GDPValClaude Opus 4.6 by 12.255.943.7+12.2
- AA ApexAgentstie3333.7tie
ReasoningClaude Opus 4.6
- ARC-AGI-2Claude Opus 4.6 by 4668.822.8+46
- LiveBench · ReasoningClaude Opus 4.6 by 10.188.778.6+10.1
- SimpleBenchClaude Opus 4.6 by 8.867.658.8+8.8
- CritPtGLM-5.2 by 8.312.620.9+8.3
- Humanity's Last ExamGLM-5.2 by 1.239.941.1+1.2
- GPQA Diamondtie89.689.5tie
FactsClaude Opus 4.6
- AA-Omniscience · Non-hallucinationGLM-5.2 by 36.537.273.7+36.5
- AA-Omniscience · AccuracyClaude Opus 4.6 by 22.74724.3+22.7
- SimpleQA VerifiedClaude Opus 4.6 by 12.84734.2+12.8
MathGLM-5.2
- IMOAnswerBenchGLM-5.2 by 15.775.391+15.7
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.6 by 6.86659.2+6.8
- HMMT Feb. 2026Claude Opus 4.6 by 3.796.292.5+3.7
- AIME 2026GLM-5.2 by 2.596.799.2+2.5
- FrontierMath Tier 4GLM-5.2 by 2.526.829.3+2.5
- LiveBench · Mathematicstie89.389.8tie
Following instructionsEven
- IFBenchGLM-5.2 by 20.253.173.3+20.2
- LiveBench · Instruction FollowingClaude Opus 4.6 by 163.362.3+1
Other results17 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 28.267.639.4+28.2
- Artificial Analysis Coding IndexGLM-5.2 by 20.748.168.8+20.7
- ARC-AGI-1Claude Opus 4.6 by 169377+16
- OfficeQA ProClaude Opus 4.6 by 15.757.141.4+15.7
- AA-OmniscienceClaude Opus 4.6 by 9.313.74.4+9.3
- ToolathlonClaude Opus 4.6 by 8.656.848.2+8.6
- livebench_languageClaude Opus 4.6 by 7.183.376.2+7.1
- τ²-Bench Telecom (AA run)GLM-5.2 by 792.199.1+7
- JobBenchGLM-5.2 by 6.836.643.4+6.8
- HiL-Bench (Tools-allowed)GLM-5.2 by 5.438.343.7+5.4
- livebench_data_analysisGLM-5.2 by 3.869.973.7+3.8
- CyberGymGLM-5.2 by 3.473.877.2+3.4
- HMMT Nov. 2025Claude Opus 4.6 by 1.996.394.4+1.9
- AA IntelligenceGLM-5.2 by 1.831.933.7+1.8
- HLE (with tools)GLM-5.2 by 1.453.354.7+1.4
- Tool-DecathlonGLM-5.2 by 147.248.2+1
- NL2Repotie49.848.9tie
Questions people ask
Which is better, Claude Opus 4.6 or GLM-5.2?
Claude Opus 4.6 and GLM-5.2 each win two of the seven areas where both have results. Claude Opus 4.6 wins reasoning and facts; GLM-5.2 wins coding and math. GLM-5.2 costs 81% less. They are level on agents, long documents and following instructions.
Which is better for coding?
GLM-5.2. It wins 5 of the 6 coding tests both models report; Claude Opus 4.6 wins none, and 1 is a tie.
Which is cheaper?
Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; GLM-5.2 costs $1.40 and $4.40. That makes GLM-5.2 about 81% 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 27 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 17 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.