Claude Sonnet 5 vs GLM-5.3
Wins 1 of 7 areas
Long documents
Wins 5 of 7 areas
Coding · Agents · Reasoning · Facts · Following instructions
GLM-5.3 is the stronger all-rounder.Claude Sonnet 5 is better at long documents.
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 software14GLM-5.34 of 5 tests
- AgentsCarrying out multi-step tasks on its own03GLM-5.33 of 3 tests
- ReasoningHard problems that need careful thinking13GLM-5.33 of 5 tests · 1 tie
- FactsGetting facts right instead of making them up12GLM-5.32 of 3 tests
- Following instructionsDoing exactly what it is asked01GLM-5.31 of 1 test
- Long documentsFinding answers in very long texts10Claude Sonnet 51 of 1 test
- MathCompetition and research-level math11Even1 each · 1 tie
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.
GLM-5.3 costs 52% 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-5.3 pulls ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+27.8points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+13points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+9.8points ahead
Where Claude Sonnet 5 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.2points ahead
- Fresh competition math problemsLiveBench · Mathematics+5points ahead
- Fresh logic puzzles that change regularlyLiveBench · Reasoning+2.9points 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-5.3
- LMArena · WebDevGLM-5.3 by 83 rating points15391622+83 rating
- SciCodeGLM-5.3 by 4.754.359+4.7
- Terminal-Bench 2.1GLM-5.3 by 3.480.583.9+3.4
- LiveBench · CodingClaude Sonnet 5 by 1.780.779+1.7
- LiveBench · Agentic CodingGLM-5.3 by 1.559.460.9+1.5
AgentsGLM-5.3
- Terminal-Bench 4.0GLM-5.3 by 27.814.141.9+27.8
- τ-Bench V3 · BankingGLM-5.3 by 1337.350.3+13
- GDPValGLM-5.3 by 9.348.257.5+9.3
ReasoningGLM-5.3
- SimpleBenchGLM-5.3 by 5.660.666.2+5.6
- LiveBench · ReasoningClaude Sonnet 5 by 2.988.785.8+2.9
- CritPtGLM-5.3 by 2.216.919.1+2.2
- Humanity's Last ExamGLM-5.3 by 141.342.3+1
- GPQA Diamondtie91.191.7tie
FactsGLM-5.3
- AA-Omniscience · Non-hallucinationGLM-5.3 by 9.860.670.4+9.8
- SimpleQA VerifiedGLM-5.3 by 7.333.741+7.3
- AA-Omniscience · AccuracyClaude Sonnet 5 by 6.24033.9+6.2
MathEven
- LiveBench · MathematicsClaude Sonnet 5 by 592.987.9+5
- FrontierMath Tiers 1-3 (v2)GLM-5.3 by 3.265.668.8+3.2
- FrontierMath Tier 4tie29.329.3tie
Following instructionsGLM-5.3
- LiveBench · Instruction FollowingGLM-5.3 by 5.463.969.3+5.4
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.
- GDP (Surge AI)Claude Sonnet 5 by 70.481.611.2+70.4
- Program BenchClaude Sonnet 5 by 58.377.319+58.3
- Terminal-Bench 4.0GLM-5.3 by 29.412.441.8+29.4
- ToolathlonGLM-5.3 by 18.754.373+18.7
- GDPval-AA v2GLM-5.3 by 151 rating points16181769+151 rating
- Terminal-bench 3.0GLM-5.3 by 13.714.628.3+13.7
- DeepSWE 1.1GLM-5.3 by 12.95466.9+12.9
- AA Agentic IndexGLM-5.3 by 9.144.353.4+9.1
- AA IntelligenceGLM-5.3 by 6.638.244.8+6.6
- HLE (with tools)GLM-5.3 by 5.157.462.5+5.1
- HealthBench ProfessionalClaude Sonnet 5 by 557.852.8+5
- livebench_languageGLM-5.3 by 4.97579.9+4.9
- HealthBenchClaude Sonnet 5 by 4.759.254.5+4.7
- Artificial Analysis Coding IndexGLM-5.3 by 3.371.574.8+3.3
- AA-OmniscienceClaude Sonnet 5 by 2.216.414.3+2.2
- Toolathlon VerifiedClaude Sonnet 5 by 1.774.773+1.7
- livebench_data_analysisClaude Sonnet 5 by 1.571.770.2+1.5
Questions people ask
Which is better, Claude Sonnet 5 or GLM-5.3?
GLM-5.3 wins five of the seven areas where both have results: coding, agents, reasoning, facts and following instructions. Claude Sonnet 5 wins long documents. They are level on math.
Which is better for coding?
GLM-5.3. It wins 4 of the 5 coding tests both models report; Claude Sonnet 5 wins 1.
Which is cheaper?
Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; GLM-5.3 costs $1.40 and $4.40. That makes GLM-5.3 about 52% 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 21 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.