Model comparison
Gemma 3 27B vs GLM-5
GLM-5 is the stronger model overall, scoring 46.1 to 30.8 on the Noometry Index. Gemma 3 27B costs 16× less per token, which makes it the better buy when GLM-5'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 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 25.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 22.5% for Gemma 3 27B and 80% for GLM-5.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $1 / $3.20 for GLM-5.
- GLM-5 accepts more context: 205K tokens versus 131K.
Side by side
| Gemma 3 27B | GLM-5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 30.8 | 46.1 |
| Released | 2025-03-11 | 2026-02-11 |
| Weights | Open | Open |
| Context window | 131K | 205K |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.08 | $1 |
| Output $ / M tokens | $0.16 | $3.20 |
| Results tracked | 43 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
Gemma 3 27B: 22.5 (#334), GLM-5: 49.0 (#52)
| Benchmark | Gemma 3 27B | GLM-5 |
|---|---|---|
| LMArena Coding | 1322 | 1461 |
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| Aider Polyglot | 4.9% | — |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| SciCode | 21.2% | — |
| WeirdML | — | 48.2% |
| LiveBench Coding | 39.9% | — |
| ALE-Bench | — | 765.62 |
Agentic & Tool Use GLM-5 leads
Gemma 3 27B: 25.1 (#110), GLM-5: 31.1 (#71)
| Benchmark | Gemma 3 27B | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| Berkeley Function Calling Leaderboard | 29.5% | — |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| Vending-Bench 2 | — | 4,432 |
Reasoning GLM-5 leads
Gemma 3 27B: 16.7 (#301), GLM-5: 27.6 (#116)
| Benchmark | Gemma 3 27B | GLM-5 |
|---|---|---|
| Kagi LLM Benchmark | 40.4% | 75% |
| Chess Puzzles | 0% | 10% |
| LMArena Hard Prompts | 1340 | 1452 |
| Epoch Capabilities Index | 130.04 | 145.83 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 53.2% |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | — | 44.7% |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| ForecastBench | — | 61 |
| LiveBench | 50% | — |
Math GLM-5 leads
Gemma 3 27B: 25.9 (#265), GLM-5: 46.4 (#71)
| Benchmark | Gemma 3 27B | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 22.5% | 80% |
| LMArena Math | 1312 | 1440 |
| MathArena Final-Answer Competitions | — | 65.7% |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-5 leads
Gemma 3 27B: 25.5 (#261), GLM-5: 52.3 (#64)
| Benchmark | Gemma 3 27B | GLM-5 |
|---|---|---|
| GPQA Diamond | 47.7% | 87.8% |
| Vectara Hallucination Rate | 7.4% | 10.1% |
| LMArena Expert | 1304 | 1454 |
| Confabulations | 40.3% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), GLM-5: —
| Benchmark | Gemma 3 27B | GLM-5 |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual GLM-5 leads
Gemma 3 27B: 46.9 (#155), GLM-5: 53.7 (#58)
| Benchmark | Gemma 3 27B | GLM-5 |
|---|---|---|
| LMArena Non-English | 1334 | 1430 |
| LMArena Chinese | 1346 | 1511 |
| LMArena French | 1368 | 1455 |
| LMArena German | 1362 | 1445 |
| LMArena Japanese | 1287 | 1416 |
| LMArena Korean | 1308 | 1423 |
| LMArena Russian | 1349 | 1436 |
| LMArena Spanish | 1349 | 1454 |
Instruction Following GLM-5 leads
Gemma 3 27B: 70.6 (#160), GLM-5: 75.2 (#67)
| Benchmark | Gemma 3 27B | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1321 | 1428 |
| LiveBench Instruction Following | 74.9% | — |
Long Context GLM-5 leads
Gemma 3 27B: 27.6 (#293), GLM-5: 44.7 (#60)
| Benchmark | Gemma 3 27B | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1333 | 1446 |
| Fiction.LiveBench | 33.3% | — |
| CL-bench | — | 18.7% |
Writing & Preference GLM-5 leads
Gemma 3 27B: 52.5 (#168), GLM-5: 66.0 (#38)
| Benchmark | Gemma 3 27B | GLM-5 |
|---|---|---|
| LMArena Text | 1358 | 1446 |
| LMArena Creative Writing | 1346 | 1439 |
| EQ-Bench Creative Writing | 1266 | 1601 |
| LMArena Multi-Turn | 1345 | 1456 |
| Short-Story Creative Writing | 79.9% | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than GLM-5?
GLM-5 is the stronger model overall, scoring 46.1 to 30.8 on the Noometry Index. Gemma 3 27B costs 16× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or GLM-5?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; GLM-5 lists at $1 and $3.20.
Is Gemma 3 27B or GLM-5 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 131K.
How many benchmarks do Gemma 3 27B and GLM-5 share?
24 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and GLM-5 has 45.