Model comparison
Gemma 2 27B vs GLM-4.6
GLM-4.6 is the stronger model overall, scoring 41.4 to 29.4 on the Noometry Index. Gemma 2 27B costs 1.5× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
GoogleSummary
- They share 17 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and GLM-4.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.6 leads 39.1 to 10.7.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- GLM-4.6 accepts more context: 205K tokens versus 8K.
Side by side
| Gemma 2 27B | GLM-4.6 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 29.4 | 41.4 |
| Released | 2024-06-24 | 2025-09-30 |
| Weights | Open | Open |
| Context window | 8K | 205K |
| Max output | 2K | 131K |
| Input $ / M tokens | $0.65 | $0.60 |
| Output $ / M tokens | $0.65 | $2.20 |
| Results tracked | 34 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
Gemma 2 27B: 34.1 (#246), GLM-4.6: 40.1 (#148)
| Benchmark | Gemma 2 27B | GLM-4.6 |
|---|---|---|
| LMArena Coding | 1211 | 1449 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1340 |
| SciCode | — | 38.4% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | — | 340.82 |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, GLM-4.6: 32.3 (#66)
| Benchmark | Gemma 2 27B | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |
Reasoning GLM-4.6 leads
Gemma 2 27B: 15.3 (#315), GLM-4.6: 23.7 (#172)
| Benchmark | Gemma 2 27B | GLM-4.6 |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1440 |
| Kagi LLM Benchmark | — | 47.4% |
| CritPt | — | 1.1% |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| Epoch Capabilities Index | 122.08 | — |
| LiveBench | 38.2% | — |
Math GLM-4.6 leads
Gemma 2 27B: 10.7 (#311), GLM-4.6: 39.1 (#111)
| Benchmark | Gemma 2 27B | GLM-4.6 |
|---|---|---|
| LMArena Math | 1212 | 1432 |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-4.6 leads
Gemma 2 27B: 19.0 (#280), GLM-4.6: 40.2 (#124)
| Benchmark | Gemma 2 27B | GLM-4.6 |
|---|---|---|
| LMArena Expert | 1172 | 1431 |
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| Vectara Hallucination Rate | — | 9.5% |
| MMLU | 75.7% | — |
Multilingual GLM-4.6 leads
Gemma 2 27B: 38.6 (#226), GLM-4.6: 53.5 (#66)
| Benchmark | Gemma 2 27B | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1217 | 1426 |
| LMArena Chinese | 1221 | 1499 |
| LMArena French | 1247 | 1459 |
| LMArena German | 1209 | 1447 |
| LMArena Japanese | 1175 | 1393 |
| LMArena Korean | 1174 | 1400 |
| LMArena Russian | 1234 | 1419 |
| LMArena Spanish | 1228 | 1436 |
Instruction Following GLM-4.6 leads
Gemma 2 27B: 60.5 (#249), GLM-4.6: 74.3 (#98)
| Benchmark | Gemma 2 27B | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1206 | 1410 |
| LiveBench Instruction Following | 58.1% | — |
Long Context GLM-4.6 leads
Gemma 2 27B: 37.3 (#218), GLM-4.6: 43.4 (#94)
| Benchmark | Gemma 2 27B | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1231 | 1422 |
Writing & Preference GLM-4.6 leads
Gemma 2 27B: 44.2 (#225), GLM-4.6: 61.1 (#90)
| Benchmark | Gemma 2 27B | GLM-4.6 |
|---|---|---|
| LMArena Text | 1231 | 1440 |
| LMArena Creative Writing | 1241 | 1411 |
| LMArena Multi-Turn | 1224 | 1427 |
| EQ-Bench Creative Writing | — | 1411 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than GLM-4.6?
GLM-4.6 is the stronger model overall, scoring 41.4 to 29.4 on the Noometry Index. Gemma 2 27B costs 1.5× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Which is cheaper, Gemma 2 27B or GLM-4.6?
Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is Gemma 2 27B or GLM-4.6 better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 8K.
How many benchmarks do Gemma 2 27B and GLM-4.6 share?
17 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and GLM-4.6 has 29.