Gemma 3 27B vs GLM 4.5
Updated October 21, 2026. 40 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick GLM 4.5 for coding: it scores 64.2 on the Vibe Coding Index against 4.9 for Gemma 3 27B.
Pick Gemma 3 27B when output tokens cost 6.3x less, or when the benchmark that matters is Creative writing (Lech Mazur), where it leads.
- Shared results
- 40
- Gemma 3 27B only
- 22
- GLM 4.5 only
- 20
- Like-for-like categories
- 7 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
GLM 4.5
GLM 4.5 scores 64.2 against 4.9.
One benchmark behind each score
Intelligence
AA Intelligence Index
GLM 4.5
GLM 4.5 leads, 12.8 against 4.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemma 3 27B has a AA Agentic Index result, 0.1.
Directional only
Reasoning
GPQA Diamond
No call
Only GLM 4.5 has a GPQA Diamond result, 72.2%.
Directional only
Math
AIME
No call
Only GLM 4.5 has a AIME result, 86.7%.
Directional only
Knowledge
MMLU Pro
No call
Only GLM 4.5 has a MMLU Pro result, 81.2%.
Directional only
Web design
Design Arena: websites
No call
Only GLM 4.5 has a Design Arena: websites result, 1170.
Directional only
Long documents
Listed context window
No call
Both take 131K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 3 27B
Gemma 3 27B $0.0003, GLM 4.5 $0.0017 per turn.
List prices
At a glance
- Coding index
- Gemma 3 27B 4.9 from 1 benchmark, GLM 4.5 64.2 from 1 benchmark.
- Widest category
- Math, 35.6 points apart on average over 4 shared benchmarks.
- Widest single gap
- LiveCodeBench (Artificial Analysis run): Gemma 3 27B 13.7% against GLM 4.5 73.8%, 60.1 points apart on a 0 to 100 scale.
- Output price
- Gemma 3 27B $0.35 against GLM 4.5 $2.20 per million output tokens, 6.3x apart.
- Context window
- Both take 131K tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Gemma 3 27B | Bars | GLM 4.5 | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 4 | ||
| Knowledge | 0 | 5 | ||
| General | 1 | 19 | ||
| All shared boards | 1 | 39 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index04
| Benchmark | Gemma 3 27B | GLM 4.5 | Leader |
|---|---|---|---|
| Aider polyglot | 4.9% | Not measured | Only Gemma 3 27B measured |
| SWE-bench Verified | Not measured | 64.2% | Only GLM 4.5 measured |
| AA Coding Index | 10.1 | Not measured | Only Gemma 3 27B measured |
| LiveCodeBench (Vals AI) | Not measured | 67.5% | Only GLM 4.5 measured |
| LiveCodeBench (Artificial Analysis run) | 13.7% | 73.8% | GLM 4.5 |
| SciCode | 23.3% | Not measured | Only Gemma 3 27B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 3.8% | 22.0% | GLM 4.5 |
| WeirdML | Not measured | 40.6% | Only GLM 4.5 measured |
| ALE-Bench | Not measured | 344.8 | Only GLM 4.5 measured |
| LMArena Text: coding | 1322 | 1434 | GLM 4.5 |
| LMArena Text: software and IT | 1354 | 1440 | GLM 4.5 |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 3 27B | GLM 4.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 4.9 | 12.8 | GLM 4.5 |
| Epoch Capabilities Index | 130.0 | Not measured | Only Gemma 3 27B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 3 27B | GLM 4.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 0.1 | Not measured | Only Gemma 3 27B measured |
| τ²-Bench Telecom | 10.5% | 43.0% | GLM 4.5 |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Gemma 3 27B | GLM 4.5 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 72.2% | Only GLM 4.5 measured |
| GPQA Diamond (Artificial Analysis run) | 42.8% | 78.2% | GLM 4.5 |
| Humanity's Last Exam (Artificial Analysis run) | 4.4% | 13.0% | GLM 4.5 |
| GPQA Diamond (Epoch AI run) | 47.7% | Not measured | Only Gemma 3 27B measured |
| LMArena Text: hard prompts | 1340 | 1429 | GLM 4.5 |
| LMArena Text: expert | 1304 | 1433 | GLM 4.5 |
| LMArena Text: hard prompts in English | 1353 | 1429 | GLM 4.5 |
| LMArena Vision: diagrams | 1156 | Not measured | Only Gemma 3 27B measured |
| LMArena Vision: homework | 1160 | Not measured | Only Gemma 3 27B measured |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Gemma 3 27B | GLM 4.5 | Leader |
|---|---|---|---|
| AIME | Not measured | 86.7% | Only GLM 4.5 measured |
| MATH 500 (Vals AI) | Not measured | 94.0% | Only GLM 4.5 measured |
| MGSM (Vals AI) | Not measured | 90.8% | Only GLM 4.5 measured |
| AA Math Index | 20.7 | 73.7 | GLM 4.5 |
| AIME 2025 (Artificial Analysis run) | 20.7% | 73.7% | GLM 4.5 |
| OTIS Mock AIME | 22.5% | Not measured | Only Gemma 3 27B measured |
| MATH level 5 | 74.0% | Not measured | Only Gemma 3 27B measured |
| LMArena Text: math | 1312 | 1427 | GLM 4.5 |
| LMArena Text: mathematical work | 1327 | 1430 | GLM 4.5 |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Gemma 3 27B | GLM 4.5 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 81.2% | Only GLM 4.5 measured |
| LegalBench (Vals AI) | Not measured | 75.6% | Only GLM 4.5 measured |
| CorpFin (Vals AI) | Not measured | 61.0% | Only GLM 4.5 measured |
| TaxEval (Vals AI) | Not measured | 72.4% | Only GLM 4.5 measured |
| MedQA (Vals AI) | Not measured | 90.0% | Only GLM 4.5 measured |
| MMLU Pro (Artificial Analysis run) | 66.9% | 83.5% | GLM 4.5 |
| GeoBench | 52.0% | Not measured | Only Gemma 3 27B measured |
| LMArena Text: science | 1383 | 1444 | GLM 4.5 |
| LMArena Text: medicine and healthcare | 1391 | 1455 | GLM 4.5 |
| LMArena Text: legal and government | 1375 | 1438 | GLM 4.5 |
| LMArena Text: business and finance | 1360 | 1420 | GLM 4.5 |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Gemma 3 27B | GLM 4.5 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1170 | Only GLM 4.5 measured |
| Design Arena: UI components | Not measured | 1144 | Only GLM 4.5 measured |
| Design Arena: game dev | Not measured | 1145 | Only GLM 4.5 measured |
| Design Arena: data viz | Not measured | 1159 | Only GLM 4.5 measured |
| Design Arena: 3D | Not measured | 1170 | Only GLM 4.5 measured |
| Design Arena: all code categories | Not measured | 1165 | Only GLM 4.5 measured |
| Design Arena: SVG | Not measured | 1096 | Only GLM 4.5 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index119
| Benchmark | Gemma 3 27B | GLM 4.5 | Leader |
|---|---|---|---|
| IFBench | 31.8% | 44.1% | GLM 4.5 |
| Long context reasoning (AA-LCR) | 7.3% | 52.7% | GLM 4.5 |
| DTBench | 52.5% | Not measured | Only Gemma 3 27B measured |
| LMCA | 12.3% | Not measured | Only Gemma 3 27B measured |
| Fiction.LiveBench | 33.3% | Not measured | Only Gemma 3 27B measured |
| Creative writing (Lech Mazur) | 79.9% | 73.4% | Gemma 3 27B |
| LMArena Text | 1358 | 1430 | GLM 4.5 |
| LMArena Text: instruction following | 1321 | 1404 | GLM 4.5 |
| LMArena Text: creative writing | 1345 | 1395 | GLM 4.5 |
| LMArena Vision | 1165 | Not measured | Only Gemma 3 27B measured |
| LMArena Text: English | 1377 | 1437 | GLM 4.5 |
| LMArena Text: non-English | 1334 | 1417 | GLM 4.5 |
| LMArena Text: Chinese | 1346 | 1465 | GLM 4.5 |
| LMArena Text: German | 1362 | 1407 | GLM 4.5 |
| LMArena Text: Japanese | 1287 | 1415 | GLM 4.5 |
| LMArena Text: Korean | 1308 | 1380 | GLM 4.5 |
| LMArena Text: French | 1368 | 1418 | GLM 4.5 |
| LMArena Text: Spanish | 1349 | 1454 | GLM 4.5 |
| LMArena Text: Russian | 1349 | 1413 | GLM 4.5 |
| LMArena Text: Polish | 1345 | 1422 | GLM 4.5 |
| LMArena Text: multi-turn | 1345 | 1415 | GLM 4.5 |
| LMArena Text: longer queries | 1333 | 1412 | GLM 4.5 |
| LMArena Text: writing and language | 1347 | 1403 | GLM 4.5 |
| LMArena Text: entertainment and media | 1320 | 1404 | GLM 4.5 |
| LMArena Vision: English | 1188 | Not measured | Only Gemma 3 27B measured |
| LMArena Vision: Chinese | 1164 | Not measured | Only Gemma 3 27B measured |
| LMArena Vision: reading text | 1156 | Not measured | Only Gemma 3 27B measured |
| LMArena Vision: humor | 1166 | Not measured | Only Gemma 3 27B measured |
| LMArena Vision: captioning | 1151 | Not measured | Only Gemma 3 27B measured |
| LMArena Vision: recognizing things | 1196 | Not measured | Only Gemma 3 27B measured |
| LMArena Vision: creative writing | 1177 | Not measured | Only Gemma 3 27B measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 3 27B | GLM 4.5 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemma 3 27B costs less
Repository review
50K input + 3K output tokens
Gemma 3 27B costs less
Agent loop
200K input + 10K output tokens
Gemma 3 27B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Google Gemma 3 27B | Z.ai GLM 4.5 |
|---|---|---|
| Maker | Z.ai | |
| Weights | Open weights | Open weights |
| Released | March 12, 2025 | July 25, 2025 |
| Context window | 131K | 131K |
| Input $/Mtok | $0.08 | $0.60 |
| Output $/Mtok | $0.35 | $2.20 |
| Coding index | 4.9 | 64.2 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 3 27B better than GLM 4.5 for coding?
Pick GLM 4.5 for coding: it scores 64.2 on the Vibe Coding Index against 4.9 for Gemma 3 27B. Pick Gemma 3 27B when output tokens cost 6.3x less, or when the benchmark that matters is Creative writing (Lech Mazur), where it leads.
Which is cheaper, Gemma 3 27B or GLM 4.5?
Gemma 3 27B costs $0.08 per million input tokens and $0.35 per million output tokens; GLM 4.5 costs $0.60 and $2.20. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemma 3 27B or GLM 4.5?
Neither: both take 131K tokens.
How many benchmarks is the Gemma 3 27B vs GLM 4.5 comparison based on?
40 benchmarks have a result for both models as of October 21, 2026. Gemma 3 27B's coding index rests on 1 independent benchmark and GLM 4.5's on 1. Where only one model has a result, the page says so instead of naming a winner.