GLM-5.3 is the stronger all-rounder.
Scores updated · 16 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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.
- AgentsCarrying out multi-step tasks on its own30GLM-5.33 of 3 tests
- CodingWriting and fixing software20GLM-5.32 of 2 tests
- FactsGetting facts right instead of making them up20GLM-5.32 of 2 tests
- ReasoningHard problems that need careful thinking11Even1 each · 2 ties
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
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-5.3 costs 27% 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-5.3 pulls ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+30.8points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+9.6points ahead
- Code for real scientific research problemsSciCode+4.9points ahead
Where Qwen3.8 2.4T A95B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+1.8points ahead
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGLM-5.3
- SciCodeGLM-5.3 by 4.95954.1+4.9
- Terminal-Bench 2.1GLM-5.3 by 1.983.982+1.9
AgentsGLM-5.3
- Terminal-Bench 4.0GLM-5.3 by 30.841.911.1+30.8
- GDPValGLM-5.3 by 1.957.555.6+1.9
- τ-Bench V3 · BankingGLM-5.3 by 1.250.349.1+1.2
ReasoningEven
- SimpleBenchGLM-5.3 by 3.766.262.5+3.7
- GPQA DiamondQwen3.8 2.4T A95B by 1.891.793.5+1.8
- CritPttie19.120tie
- Humanity's Last Examtie42.342.4tie
FactsGLM-5.3
- AA-Omniscience · Non-hallucinationGLM-5.3 by 9.670.460.8+9.6
- AA-Omniscience · AccuracyGLM-5.3 by 2.633.931.3+2.6
Other results4 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-5.3 by 1014.34.3+10
- AA IntelligenceGLM-5.3 by 4.944.839.9+4.9
- AA Agentic IndexGLM-5.3 by 353.450.4+3
- Artificial Analysis Coding IndexGLM-5.3 by 2.974.871.9+2.9
Questions people ask
Which is better, GLM-5.3 or Qwen3.8 2.4T A95B?
GLM-5.3 wins three of the five areas where both have results: coding, agents and facts. Qwen3.8 2.4T A95B wins none. They are level on reasoning and long documents.
Which is better for coding?
GLM-5.3. It wins 2 of the 2 coding tests both models report; Qwen3.8 2.4T A95B wins none.
Which is cheaper?
GLM-5.3 costs $1.40 per million input tokens and $4.40 per million output tokens; Qwen3.8 2.4T A95B costs $2.00 and $6.00. That makes GLM-5.3 about 27% cheaper for the same work.
How do you compare the two?
We use the 16 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 4 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.