Model comparison
Gemma 3 27B vs GLM-5.3-Flash
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 30.5 on the Noometry Index. Gemma 3 27B costs 2.4× less per token, which makes it the better buy when GLM-5.3-Flash's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Gemma 3 27B scores higher in 0 categories and GLM-5.3-Flash in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.3-Flash leads 58.4 to 25.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 22.5% for Gemma 3 27B and 93.9% for GLM-5.3-Flash.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.15 / $0.50 for GLM-5.3-Flash.
- GLM-5.3-Flash accepts more context: 1M tokens versus 131K.
Side by side
| Gemma 3 27B | GLM-5.3-Flash | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 30.5 | 49.6 |
| Released | 2025-03-11 | 2026-08-20 |
| Weights | Open | Open |
| Context window | 131K | 1M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.08 | $0.15 |
| Output $ / M tokens | $0.16 | $0.50 |
| Results tracked | 43 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
Gemma 3 27B: 22.1 (#329), GLM-5.3-Flash: 53.7 (#26)
| Benchmark | Gemma 3 27B | GLM-5.3-Flash |
|---|---|---|
| SciCode | 21.2% | 51.6% |
| LMArena Coding | 1322 | 1506 |
| DeepSWE | — | 63.4% |
| FrontierCode | — | 31.8% |
| Aider Polyglot | 4.9% | — |
| LMArena WebDev | — | 1614 |
| LiveBench Coding | 39.9% | — |
| ALE-Bench | — | 303.55 |
Agentic & Tool Use GLM-5.3-Flash leads
Gemma 3 27B: 24.9 (#105), GLM-5.3-Flash: 34.3 (#41)
| Benchmark | Gemma 3 27B | GLM-5.3-Flash |
|---|---|---|
| APEX-Agents | — | 52.8% |
| Berkeley Function Calling Leaderboard | 29.5% | — |
| GDP.pdf | — | 14% |
Reasoning GLM-5.3-Flash leads
Gemma 3 27B: 16.3 (#297), GLM-5.3-Flash: 31.7 (#69)
| Benchmark | Gemma 3 27B | GLM-5.3-Flash |
|---|---|---|
| CritPt | 0% | 15.4% |
| Chess Puzzles | 0% | 14% |
| LMArena Hard Prompts | 1340 | 1490 |
| Epoch Capabilities Index | 130.04 | 151.9 |
| Kagi LLM Benchmark | 40.4% | — |
| LiveBench Reasoning | 43.8% | — |
| Mystery Game Puzzles | — | 8% |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Surface Evolver Bench | — | 52.5% |
| Bench to the Future 3 | — | 0.15 |
| LiveBench | 50% | — |
Math GLM-5.3-Flash leads
Gemma 3 27B: 24.4 (#261), GLM-5.3-Flash: 53.1 (#38)
| Benchmark | Gemma 3 27B | GLM-5.3-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 22.5% | 93.9% |
| LMArena Math | 1312 | 1499 |
| FrontierMath (Tiers 1-3) | — | 55.8% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 21% |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge GLM-5.3-Flash leads
Gemma 3 27B: 25.4 (#256), GLM-5.3-Flash: 58.4 (#33)
| Benchmark | Gemma 3 27B | GLM-5.3-Flash |
|---|---|---|
| GPQA Diamond | 47.7% | 90.2% |
| LMArena Expert | 1303 | 1512 |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal GLM-5.3-Flash leads
Gemma 3 27B: 32.0 (#94), GLM-5.3-Flash: 42.6 (#25)
| Benchmark | Gemma 3 27B | GLM-5.3-Flash |
|---|---|---|
| LMArena Vision | 1165 | 1304 |
| GeoBench | 52% | — |
Multilingual GLM-5.3-Flash leads
Gemma 3 27B: 47.0 (#150), GLM-5.3-Flash: 56.2 (#24)
| Benchmark | Gemma 3 27B | GLM-5.3-Flash |
|---|---|---|
| LMArena Non-English | 1334 | 1462 |
| LMArena Chinese | 1347 | 1529 |
| LMArena French | 1368 | 1495 |
| LMArena German | 1362 | 1457 |
| LMArena Japanese | 1287 | 1420 |
| LMArena Korean | 1308 | 1443 |
| LMArena Russian | 1349 | 1472 |
| LMArena Spanish | 1348 | 1471 |
Instruction Following GLM-5.3-Flash leads
Gemma 3 27B: 70.8 (#155), GLM-5.3-Flash: 77.8 (#17)
| Benchmark | Gemma 3 27B | GLM-5.3-Flash |
|---|---|---|
| LMArena Instruction Following | 1321 | 1480 |
| LiveBench Instruction Following | 74.9% | — |
Long Context GLM-5.3-Flash leads
Gemma 3 27B: 27.6 (#288), GLM-5.3-Flash: 45.3 (#41)
| Benchmark | Gemma 3 27B | GLM-5.3-Flash |
|---|---|---|
| LMArena Longer Query | 1333 | 1479 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference GLM-5.3-Flash leads
Gemma 3 27B: 52.7 (#161), GLM-5.3-Flash: 65.4 (#49)
| Benchmark | Gemma 3 27B | GLM-5.3-Flash |
|---|---|---|
| LMArena Text | 1358 | 1471 |
| LMArena Creative Writing | 1346 | 1440 |
| LMArena Multi-Turn | 1344 | 1471 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than GLM-5.3-Flash?
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 30.5 on the Noometry Index. Gemma 3 27B costs 2.4× less per token, which makes it the better buy when GLM-5.3-Flash's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or GLM-5.3-Flash?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; GLM-5.3-Flash lists at $0.15 and $0.50.
Is Gemma 3 27B or GLM-5.3-Flash better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 22.1 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 131K.
How many benchmarks do Gemma 3 27B and GLM-5.3-Flash share?
24 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and GLM-5.3-Flash has 36.