Model comparison
Gemma 3 27B vs GLM-5.1
GLM-5.1 is the stronger model overall, scoring 47.8 to 30.8 on the Noometry Index. Gemma 3 27B costs 21× less per token, which makes it the better buy when GLM-5.1'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 1 category and GLM-5.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.1 leads 54.9 to 25.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 22.5% for Gemma 3 27B and 93.3% for GLM-5.1.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 131K.
Side by side
| Gemma 3 27B | GLM-5.1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 30.8 | 47.8 |
| Released | 2025-03-11 | 2026-04-07 |
| Weights | Open | Open |
| Context window | 131K | 200K |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.08 | $1.40 |
| Output $ / M tokens | $0.16 | $4.40 |
| Results tracked | 43 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
Gemma 3 27B: 22.5 (#334), GLM-5.1: 48.7 (#55)
| Benchmark | Gemma 3 27B | GLM-5.1 |
|---|---|---|
| SciCode | 21.2% | 43.8% |
| LMArena Coding | 1322 | 1485 |
| SWE-bench Verified | — | 74.2% |
| Aider Polyglot | 4.9% | — |
| LMArena WebDev | — | 1508 |
| WeirdML | — | 57.1% |
| LiveBench Coding | 39.9% | — |
| ALE-Bench | — | 887.1 |
Agentic & Tool Use Too close to call
Gemma 3 27B: 25.1 (#110), GLM-5.1: 24.9 (#113)
| Benchmark | Gemma 3 27B | GLM-5.1 |
|---|---|---|
| APEX-Agents | — | 40.9% |
| Berkeley Function Calling Leaderboard | 29.5% | — |
| ExploitBench | — | 18.1% |
| GBAEval | — | 0% |
| Vending-Bench 2 | — | 5,634 |
Reasoning GLM-5.1 leads
Gemma 3 27B: 16.7 (#301), GLM-5.1: 39.1 (#60)
| Benchmark | Gemma 3 27B | GLM-5.1 |
|---|---|---|
| CritPt | 0% | 4.6% |
| Chess Puzzles | 0% | 19% |
| LMArena Hard Prompts | 1340 | 1472 |
| Epoch Capabilities Index | 130.04 | 149.84 |
| SimpleBench | — | 55.1% |
| Kagi LLM Benchmark | 40.4% | — |
| NYT Connections (extended) | — | 77.7% |
| Thematic Generalization | — | 69.8% |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| LiveBench | 50% | — |
Math GLM-5.1 leads
Gemma 3 27B: 25.9 (#265), GLM-5.1: 49.7 (#60)
| Benchmark | Gemma 3 27B | GLM-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 22.5% | 93.3% |
| LMArena Math | 1312 | 1473 |
| FrontierMath (Tiers 1-3) | — | 36.8% |
| MathArena Final-Answer Competitions | — | 67.1% |
| ProofBench | — | 22.2% |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
| FrontierMath (Feb 2025 set) | — | 33.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GLM-5.1 leads
Gemma 3 27B: 25.5 (#261), GLM-5.1: 54.9 (#50)
| Benchmark | Gemma 3 27B | GLM-5.1 |
|---|---|---|
| GPQA Diamond | 47.7% | 89.9% |
| LMArena Expert | 1304 | 1476 |
| SimpleQA Verified | — | 34% |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), GLM-5.1: —
| Benchmark | Gemma 3 27B | GLM-5.1 |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual GLM-5.1 leads
Gemma 3 27B: 46.9 (#155), GLM-5.1: 55.0 (#36)
| Benchmark | Gemma 3 27B | GLM-5.1 |
|---|---|---|
| LMArena Non-English | 1334 | 1447 |
| LMArena Chinese | 1346 | 1515 |
| LMArena French | 1368 | 1474 |
| LMArena German | 1362 | 1465 |
| LMArena Japanese | 1287 | 1434 |
| LMArena Korean | 1308 | 1418 |
| LMArena Russian | 1349 | 1454 |
| LMArena Spanish | 1349 | 1469 |
Instruction Following GLM-5.1 leads
Gemma 3 27B: 70.6 (#160), GLM-5.1: 76.3 (#42)
| Benchmark | Gemma 3 27B | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | 1321 | 1451 |
| LiveBench Instruction Following | 74.9% | — |
Long Context GLM-5.1 leads
Gemma 3 27B: 27.6 (#293), GLM-5.1: 44.9 (#53)
| Benchmark | Gemma 3 27B | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | 1333 | 1466 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference GLM-5.1 leads
Gemma 3 27B: 52.5 (#168), GLM-5.1: 66.9 (#31)
| Benchmark | Gemma 3 27B | GLM-5.1 |
|---|---|---|
| LMArena Text | 1358 | 1461 |
| LMArena Creative Writing | 1346 | 1453 |
| EQ-Bench Creative Writing | 1266 | 1592 |
| LMArena Multi-Turn | 1345 | 1472 |
| Short-Story Creative Writing | 79.9% | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than GLM-5.1?
GLM-5.1 is the stronger model overall, scoring 47.8 to 30.8 on the Noometry Index. Gemma 3 27B costs 21× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or GLM-5.1?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is Gemma 3 27B or GLM-5.1 better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
GLM-5.1 does, with 200K tokens against 131K.
How many benchmarks do Gemma 3 27B and GLM-5.1 share?
24 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and GLM-5.1 has 41.