GLM-4.5 vs GLM-4.5-Air
Wins 5 of 6 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
GLM-4.5 is the stronger all-rounder.GLM-4.5-Air is cheaper.
Scores updated · 25 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 software30GLM-4.53 of 3 tests
- ReasoningHard problems that need careful thinking20GLM-4.52 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up20GLM-4.52 of 2 tests
- Long documentsFinding answers in very long texts10GLM-4.51 of 1 test
- Following instructionsDoing exactly what it is asked10GLM-4.51 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each
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-4.5-Air costs 59% 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-4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+22.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+8.8points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+6.6points ahead
Where GLM-4.5-Air pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 25 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGLM-4.5
- SWE-bench VerifiedGLM-4.5 by 6.664.257.6+6.6
- SciCodeGLM-4.5 by 4.234.830.6+4.2
- Terminal-Bench HardGLM-4.5 by 1.52220.5+1.5
ReasoningGLM-4.5
- Humanity's Last ExamGLM-4.5 by 6137+6
- GPQA DiamondGLM-4.5 by 4.978.273.3+4.9
- CritPttie00tie
FactsGLM-4.5
- AA-Omniscience · Non-hallucinationGLM-4.5 by 22.829.97.1+22.8
- AA-Omniscience · AccuracyGLM-4.5 by 8.825.116.3+8.8
Other results13 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-4.5 by 34.1-27.4-61.5+34.1
- AIME 2025GLM-4.5 by 1093.383.3+10
- Terminal-BenchGLM-4.5 by 7.537.530+7.5
- AA Agentic IndexGLM-4.5-Air by 4.816.221+4.8
- τ²-Bench Telecom (AA run)GLM-4.5-Air by 3.54346.5+3.5
- MMLU-ProGLM-4.5 by 3.284.681.4+3.2
- Artificial Analysis Coding IndexGLM-4.5 by 2.526.323.8+2.5
- LiveCodeBenchGLM-4.5 by 2.272.970.7+2.2
- TAU-bench (retail)GLM-4.5 by 1.879.777.9+1.8
- AA IntelligenceGLM-4.5 by 1.712.811.1+1.7
- BFCL v3GLM-4.5 by 1.477.876.4+1.4
- TAU-bench (airline)tie60.460.8tie
- MATH-500 (EM)tie98.298.1tie
Questions people ask
Which is better, GLM-4.5 or GLM-4.5-Air?
GLM-4.5 wins five of the six areas where both have results: coding, reasoning, facts, long documents and following instructions. GLM-4.5-Air wins none, but costs 59% less. They are level on agents.
Which is better for coding?
GLM-4.5. It wins 3 of the 3 coding tests both models report; GLM-4.5-Air wins none.
Which is cheaper?
GLM-4.5 costs $0.60 per million input tokens and $2.20 per million output tokens; GLM-4.5-Air costs $0.17 and $0.98. That makes GLM-4.5-Air about 59% cheaper for the same work.
How do you compare the two?
We use the 25 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 13 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.