Claude Opus 4.8 vs GLM-5.3-Flash
Wins 4 of 8 areas
Reasoning · Facts · Math · Following instructions
Wins 2 of 8 areas
Agents · Long documents
Claude Opus 4.8 wins more areas, narrowly.GLM-5.3-Flash is cheaper and better at agents.
Scores updated · 36 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- ReasoningHard problems that need careful thinking40Claude Opus 4.84 of 5 tests · 1 tie
- MathCompetition and research-level math30Claude Opus 4.83 of 3 tests
- FactsGetting facts right instead of making them up21Claude Opus 4.82 of 3 tests
- Following instructionsDoing exactly what it is asked10Claude Opus 4.81 of 1 test
- AgentsCarrying out multi-step tasks on its own13GLM-5.3-Flash3 of 4 tests
- Long documentsFinding answers in very long texts01GLM-5.3-Flash1 of 1 test
- CodingWriting and fixing software22Even2 each · 1 tie
- Images and chartsUnderstanding pictures, charts and video00Even0 each · 2 ties
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-Flash costs 98% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Opus 4.8 pulls ahead
- Completes tasks by operating a computer desktopOSWorld-Verified+68.6points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+39points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+24.2points ahead
Where GLM-5.3-Flash pulls ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+13points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+11.7points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+11.1points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- LiveBench · Agentic CodingGLM-5.3-Flash by 6.350.556.8+6.3
- LMArena · WebDevGLM-5.3-Flash by 49 rating points15561605+49 rating
- LiveBench · CodingClaude Opus 4.8 by 2.881.879+2.8
- SciCodeClaude Opus 4.8 by 2.854.451.6+2.8
- Terminal-Bench 2.1tie84.684.3tie
AgentsGLM-5.3-Flash
- OSWorld-VerifiedClaude Opus 4.8 by 68.683.414.8+68.6
- τ-Bench V3 · BankingGLM-5.3-Flash by 1334.247.2+13
- Terminal-Bench 4.0GLM-5.3-Flash by 11.121.732.8+11.1
- GDPValGLM-5.3-Flash by 9.547.757.2+9.5
ReasoningClaude Opus 4.8
- LiveBench · ReasoningClaude Opus 4.8 by 11.689.277.6+11.6
- Humanity's Last ExamClaude Opus 4.8 by 8.848.739.9+8.8
- ARC-AGI-2Claude Opus 4.8 by 6.372.165.8+6.3
- CritPtClaude Opus 4.8 by 5.520.915.4+5.5
- GPQA Diamondtie9291.2tie
FactsClaude Opus 4.8
- AA-Omniscience · AccuracyClaude Opus 4.8 by 21.348.827.5+21.3
- SimpleQA VerifiedClaude Opus 4.8 by 215332+21
- AA-Omniscience · Non-hallucinationGLM-5.3-Flash by 11.760.772.4+11.7
Images and chartsEven
- CharXiv (RQ)tie89.989.4tie
- LMArena · Visiontie12941296tie
MathClaude Opus 4.8
- FrontierMath Tier 4Claude Opus 4.8 by 3956.117.1+39
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.8 by 24.28055.8+24.2
- LiveBench · MathematicsClaude Opus 4.8 by 13.194.381.2+13.1
Following instructionsClaude Opus 4.8
- LiveBench · Instruction FollowingClaude Opus 4.8 by 19.27252.8+19.2
Other results12 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 4.8 by 21.328.87.5+21.3
- ToolathlonGLM-5.3-Flash by 18.559.978.4+18.5
- NL2RepoClaude Opus 4.8 by 13.469.756.3+13.4
- livebench_data_analysisGLM-5.3-Flash by 10.46676.4+10.4
- AA Agentic IndexGLM-5.3-Flash by 8.642.651.2+8.6
- DeepSWE 1.1GLM-5.3-Flash by 4.45963.4+4.4
- OfficeQA ProClaude Opus 4.8 by 3.866.262.4+3.8
- Artificial Analysis Coding IndexClaude Opus 4.8 by 2.874.371.5+2.8
- livebench_languageClaude Opus 4.8 by 2.479.777.3+2.4
- ARC-AGI-1Claude Opus 4.8 by 1.592.591+1.5
- Agents' Last Examtie25.726.3tie
- AA Intelligencetie41.841.8tie
Questions people ask
Which is better, Claude Opus 4.8 or GLM-5.3-Flash?
Claude Opus 4.8 wins four of the eight areas we test: reasoning, facts, math and following instructions. GLM-5.3-Flash wins agents and long documents, and costs 98% less. They are level on coding and images and charts.
Which is better for coding?
Neither. They win 2 coding tests each of the 5 both models report, and 1 is a tie.
Which is cheaper?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; GLM-5.3-Flash costs $0.15 and $0.50. That makes GLM-5.3-Flash about 98% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.