Model comparison
Gemma 2 27B vs GLM-4.7
GLM-4.7 is the stronger model overall, scoring 42.0 to 29.4 on the Noometry Index. Gemma 2 27B costs 1.5× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
GoogleSummary
- They share 20 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and GLM-4.7 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 19.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.4% for Gemma 2 27B and 83.3% for GLM-4.7.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- GLM-4.7 accepts more context: 205K tokens versus 8K.
Side by side
| Gemma 2 27B | GLM-4.7 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 29.4 | 42.0 |
| Released | 2024-06-24 | 2025-12-22 |
| 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 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
Gemma 2 27B: 34.1 (#246), GLM-4.7: 44.0 (#79)
| Benchmark | Gemma 2 27B | GLM-4.7 |
|---|---|---|
| LMArena Coding | 1211 | 1454 |
| LMArena WebDev | — | 1435 |
| SciCode | — | 45.1% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | — | 399.48 |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, GLM-4.7: 26.5 (#103)
| Benchmark | Gemma 2 27B | GLM-4.7 |
|---|---|---|
| Terminal-Bench | — | 33.4% |
| Vending-Bench 2 | — | 2,377 |
Reasoning GLM-4.7 leads
Gemma 2 27B: 15.3 (#315), GLM-4.7: 24.3 (#164)
| Benchmark | Gemma 2 27B | GLM-4.7 |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1443 |
| Epoch Capabilities Index | 122.08 | 143.51 |
| SimpleBench | — | 47.7% |
| CritPt | — | 1.7% |
| Chess Puzzles | — | 6% |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| LiveBench | 38.2% | — |
Math GLM-4.7 leads
Gemma 2 27B: 10.7 (#311), GLM-4.7: 38.6 (#135)
| Benchmark | Gemma 2 27B | GLM-4.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 83.3% |
| LMArena Math | 1212 | 1423 |
| ProofBench | — | 6% |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
| FrontierMath (Feb 2025 set) | — | 2.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge GLM-4.7 leads
Gemma 2 27B: 19.0 (#280), GLM-4.7: 47.0 (#80)
| Benchmark | Gemma 2 27B | GLM-4.7 |
|---|---|---|
| GPQA Diamond | 36.5% | 83.3% |
| LMArena Expert | 1172 | 1424 |
| SimpleQA Verified | — | 32.2% |
| Confabulations | 27.1% | — |
| Vectara Hallucination Rate | — | 11.7% |
| MMLU | 75.7% | — |
Multilingual GLM-4.7 leads
Gemma 2 27B: 38.6 (#226), GLM-4.7: 52.8 (#79)
| Benchmark | Gemma 2 27B | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 1217 | 1417 |
| LMArena Chinese | 1221 | 1495 |
| LMArena French | 1247 | 1432 |
| LMArena German | 1209 | 1424 |
| LMArena Japanese | 1175 | 1439 |
| LMArena Korean | 1174 | 1399 |
| LMArena Russian | 1234 | 1423 |
| LMArena Spanish | 1228 | 1434 |
Instruction Following GLM-4.7 leads
Gemma 2 27B: 60.5 (#249), GLM-4.7: 74.4 (#95)
| Benchmark | Gemma 2 27B | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1206 | 1411 |
| LiveBench Instruction Following | 58.1% | — |
Long Context GLM-4.7 leads
Gemma 2 27B: 37.3 (#218), GLM-4.7: 42.8 (#116)
| Benchmark | Gemma 2 27B | GLM-4.7 |
|---|---|---|
| LMArena Longer Query | 1231 | 1432 |
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |
Writing & Preference GLM-4.7 leads
Gemma 2 27B: 44.2 (#225), GLM-4.7: 60.9 (#93)
| Benchmark | Gemma 2 27B | GLM-4.7 |
|---|---|---|
| LMArena Text | 1231 | 1435 |
| LMArena Creative Writing | 1241 | 1401 |
| LMArena Multi-Turn | 1224 | 1446 |
| EQ-Bench Creative Writing | — | 1413 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than GLM-4.7?
GLM-4.7 is the stronger model overall, scoring 42.0 to 29.4 on the Noometry Index. Gemma 2 27B costs 1.5× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.
Which is cheaper, Gemma 2 27B or GLM-4.7?
Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.
Is Gemma 2 27B or GLM-4.7 better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
GLM-4.7 does, with 205K tokens against 8K.
How many benchmarks do Gemma 2 27B and GLM-4.7 share?
20 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and GLM-4.7 has 36.