Claude Opus 4.5 vs GLM-4.6
Wins 6 of 7 areas
Coding · Reasoning · Facts · Math · Long documents · Following instructions
Wins 0 of 7 areas
—
Claude Opus 4.5 is the stronger all-rounder.GLM-4.6 is cheaper.
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 software61Claude Opus 4.56 of 7 tests
- ReasoningHard problems that need careful thinking30Claude Opus 4.53 of 3 tests
- Following instructionsDoing exactly what it is asked20Claude Opus 4.52 of 2 tests
- FactsGetting facts right instead of making them up21Claude Opus 4.52 of 3 tests
- MathCompetition and research-level math10Claude Opus 4.51 of 1 test
- Long documentsFinding answers in very long texts10Claude Opus 4.51 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each
Math and long documents 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.
GLM-4.6 costs 91% 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 Claude Opus 4.5 pulls ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+42.3points ahead
- Real work tasks from 44 professionsGDPVal+34.3points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+33.1points ahead
Where GLM-4.6 pulls ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+46.8points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+8.1points 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.
CodingClaude Opus 4.5
- SWE-bench MultilingualGLM-4.6 by 46.8753.8+46.8
- SWE-bench ProClaude Opus 4.5 by 42.3529.7+42.3
- Terminal-Bench HardClaude Opus 4.5 by 224725+22
- SWE-bench VerifiedClaude Opus 4.5 by 12.980.968+12.9
- LMArena · WebDevClaude Opus 4.5 by 128 rating points14691341+128 rating
- SciCodeClaude Opus 4.5 by 11.149.538.4+11.1
- LiveCodeBench v6Claude Opus 4.5 by 284.882.8+2
AgentsEven
- GDPValClaude Opus 4.5 by 34.347.313+34.3
- BrowseCompGLM-4.6 by 8.13745.1+8.1
ReasoningClaude Opus 4.5
- Humanity's Last ExamClaude Opus 4.5 by 15.630.114.5+15.6
- GPQA DiamondClaude Opus 4.5 by 8.686.678+8.6
- CritPtClaude Opus 4.5 by 3.54.61.1+3.5
FactsClaude Opus 4.5
- AA-Omniscience · Non-hallucinationClaude Opus 4.5 by 33.1395.9+33.1
- AA-Omniscience · AccuracyClaude Opus 4.5 by 19.746.626.9+19.7
- Vectara HHEM hallucination ratelower is betterGLM-4.6 by 1.410.99.5+1.4
Following instructionsClaude Opus 4.5
- IFBenchClaude Opus 4.5 by 14.65843.4+14.6
- Multi-ChallengeClaude Opus 4.5 by 4.15954.9+4.1
Other results18 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-OmniscienceClaude Opus 4.5 by 55.914-41.9+55.9
- AA Agentic IndexClaude Opus 4.5 by 4159.618.6+41
- Terminal-Bench 2.0Claude Opus 4.5 by 34.859.324.5+34.8
- τ²-BenchClaude Opus 4.5 by 2398.275.2+23
- Multi-SWE-BenchClaude Opus 4.5 by 205030+20
- τ²-Bench Telecom (AA run)Claude Opus 4.5 by 1989.570.5+19
- HLE (with tools)Claude Opus 4.5 by 12.843.230.4+12.8
- AA IntelligenceClaude Opus 4.5 by 10.629.118.5+10.6
- LiveCodeBenchClaude Opus 4.5 by 7.58779.5+7.5
- MMLU-ProClaude Opus 4.5 by 6.389.583.2+6.3
- vectara_answer_rateClaude Opus 4.5 by 4.298.794.5+4.2
- vectara_avg_summary_lengthClaude Opus 4.5 by 37.3 rating points114.577.2+37.3 rating
- HMMT Feb. 2025Claude Opus 4.5 by 3.792.989.2+3.7
- frontiermath_tier_4_v1Claude Opus 4.5 by 2.14.22.1+2.1
- Artificial Analysis Coding IndexClaude Opus 4.5 by 247.845.8+2
- HMMT Nov. 2025Claude Opus 4.5 by 1.693.391.7+1.6
- vectara_factual_consistencyGLM-4.6 by 1.489.190.5+1.4
- AIME 2025GLM-4.6 by 1.192.893.9+1.1
Questions people ask
Which is better, Claude Opus 4.5 or GLM-4.6?
Claude Opus 4.5 wins six of the seven areas where both have results: coding, reasoning, facts, math, long documents and following instructions. GLM-4.6 wins none, but costs 91% less. They are level on agents.
Which is better for coding?
Claude Opus 4.5. It wins 6 of the 7 coding tests both models report; GLM-4.6 wins 1.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; GLM-4.6 costs $0.57 and $2.20. That makes GLM-4.6 about 91% 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 19 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.