GLM-4.5-Air vs Granite 4.0 Micro
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
GLM-4.5-Air is the stronger all-rounder.
Scores updated · 21 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.
- ReasoningHard problems that need careful thinking20GLM-4.5-Air2 of 3 tests · 1 tie
- CodingWriting and fixing software20GLM-4.5-Air2 of 2 tests
- FactsGetting facts right instead of making them up20GLM-4.5-Air2 of 2 tests
- AgentsCarrying out multi-step tasks on its own10GLM-4.5-Air1 of 1 test
- Long documentsFinding answers in very long texts10GLM-4.5-Air1 of 1 test
- Following instructionsDoing exactly what it is asked10GLM-4.5-Air1 of 1 test
Agents, 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.
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-Air pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+39.7points ahead
- Reasons across sets of long documentsAA-LCR+39.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+19points ahead
Where Granite 4.0 Micro pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 21 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGLM-4.5-Air
- Terminal-Bench HardGLM-4.5-Air by 1920.51.5+19
- SciCodeGLM-4.5-Air by 18.730.611.9+18.7
ReasoningGLM-4.5-Air
- GPQA DiamondGLM-4.5-Air by 39.773.333.6+39.7
- Humanity's Last ExamGLM-4.5-Air by 275+2
- CritPttie00tie
FactsGLM-4.5-Air
- AA-Omniscience · AccuracyGLM-4.5-Air by 716.39.3+7
- AA-Omniscience · Non-hallucinationGLM-4.5-Air by 2.97.14.2+2.9
Following instructionsGLM-4.5-Air
- IFBenchGLM-4.5-Air by 12.837.624.8+12.8
Other results11 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.
- MMLU-ProGLM-4.5-Air by 36.781.444.7+36.7
- τ²-Bench Telecom (AA run)GLM-4.5-Air by 33.946.512.6+33.9
- HarmBenchGranite 4.0 Micro by 30.156.186.3+30.1
- AIR-Bench 2024Granite 4.0 Micro by 23.357.180.4+23.3
- XSTestGLM-4.5-Air by 23.298.675.4+23.2
- Artificial Analysis Coding IndexGLM-4.5-Air by 18.823.85+18.8
- AA Agentic IndexGLM-4.5-Air by 16.8214.2+16.8
- AA-OmniscienceGLM-4.5-Air by 16-61.5-77.5+16
- AA IntelligenceGLM-4.5-Air by 611.15.1+6
- simple_safety_testsGranite 4.0 Micro by 199100+1
- anthropic_red_teamtie9999.6tie
Questions people ask
Which is better, GLM-4.5-Air or Granite 4.0 Micro?
GLM-4.5-Air wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. Granite 4.0 Micro wins none.
Which is better for coding?
GLM-4.5-Air. It wins 2 of the 2 coding tests both models report; Granite 4.0 Micro wins none.
How do you compare the two?
We use the 21 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.