Model comparison
Gemma 3 27B vs GLM-4.5-Air
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 30.8 on the Noometry Index. Gemma 3 27B costs 4.3× less per token, which makes it the better buy when GLM-4.5-Air's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
GoogleSummary
- They share 19 benchmarks with published results for both. Gemma 3 27B scores higher in 1 category and GLM-4.5-Air in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where GLM-4.5-Air leads 41.6 to 27.6.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.20 / $1.10 for GLM-4.5-Air.
Side by side
| Gemma 3 27B | GLM-4.5-Air | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 30.8 | 38.9 |
| Released | 2025-03-11 | 2025-07-20 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 8K | 98K |
| Input $ / M tokens | $0.08 | $0.20 |
| Output $ / M tokens | $0.16 | $1.10 |
| Results tracked | 43 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5-Air leads
Gemma 3 27B: 22.5 (#334), GLM-4.5-Air: 33.3 (#259)
| Benchmark | Gemma 3 27B | GLM-4.5-Air |
|---|---|---|
| LMArena Coding | 1322 | 1397 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| GSO | — | 2.9% |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), GLM-4.5-Air: —
| Benchmark | Gemma 3 27B | GLM-4.5-Air |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning GLM-4.5-Air leads
Gemma 3 27B: 16.7 (#301), GLM-4.5-Air: 24.1 (#166)
| Benchmark | Gemma 3 27B | GLM-4.5-Air |
|---|---|---|
| Kagi LLM Benchmark | 40.4% | 43% |
| LMArena Hard Prompts | 1340 | 1379 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| ForecastBench | — | 59.2 |
| LiveBench | 50% | — |
Math GLM-4.5-Air leads
Gemma 3 27B: 25.9 (#265), GLM-4.5-Air: 36.2 (#170)
| Benchmark | Gemma 3 27B | GLM-4.5-Air |
|---|---|---|
| LMArena Math | 1312 | 1396 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| Omni-MATH | — | 39.1% |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge GLM-4.5-Air leads
Gemma 3 27B: 25.5 (#261), GLM-4.5-Air: 35.0 (#191)
| Benchmark | Gemma 3 27B | GLM-4.5-Air |
|---|---|---|
| Vectara Hallucination Rate | 7.4% | 9.3% |
| LMArena Expert | 1304 | 1370 |
| GPQA Diamond | 47.7% | — |
| Humanity's Last Exam | — | 8.1% |
| MMLU-Pro | — | 76.2% |
| Confabulations | 40.3% | — |
| GPQA (HELM) | — | 59.4% |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), GLM-4.5-Air: —
| Benchmark | Gemma 3 27B | GLM-4.5-Air |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual GLM-4.5-Air leads
Gemma 3 27B: 46.9 (#155), GLM-4.5-Air: 49.1 (#135)
| Benchmark | Gemma 3 27B | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | 1334 | 1366 |
| LMArena Chinese | 1346 | 1426 |
| LMArena French | 1368 | 1399 |
| LMArena German | 1362 | 1377 |
| LMArena Japanese | 1287 | 1348 |
| LMArena Korean | 1308 | 1308 |
| LMArena Russian | 1349 | 1373 |
| LMArena Spanish | 1349 | 1386 |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), GLM-4.5-Air: 69.6 (#171)
| Benchmark | Gemma 3 27B | GLM-4.5-Air |
|---|---|---|
| LMArena Instruction Following | 1321 | 1354 |
| LiveBench Instruction Following | 74.9% | — |
| IFEval | — | 81.2% |
Long Context GLM-4.5-Air leads
Gemma 3 27B: 27.6 (#293), GLM-4.5-Air: 41.6 (#135)
| Benchmark | Gemma 3 27B | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | 1333 | 1366 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference GLM-4.5-Air leads
Gemma 3 27B: 52.5 (#168), GLM-4.5-Air: 55.9 (#139)
| Benchmark | Gemma 3 27B | GLM-4.5-Air |
|---|---|---|
| LMArena Text | 1358 | 1384 |
| LMArena Creative Writing | 1346 | 1343 |
| LMArena Multi-Turn | 1345 | 1371 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| WildBench | — | 78.9% |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than GLM-4.5-Air?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 30.8 on the Noometry Index. Gemma 3 27B costs 4.3× less per token, which makes it the better buy when GLM-4.5-Air's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or GLM-4.5-Air?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; GLM-4.5-Air lists at $0.20 and $1.10.
Is Gemma 3 27B or GLM-4.5-Air better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 33.3 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Gemma 3 27B and GLM-4.5-Air share?
19 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and GLM-4.5-Air has 27.