GLM 4.5 vs Llama 4 Maverick
Updated October 21, 2026. 59 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 18.1 for Llama 4 Maverick, though on 1 benchmark against 2.
Pick Llama 4 Maverick when output tokens cost 3.4x less, or when the context window is larger, 524K against 131K tokens.
- Shared results
- 59
- GLM 4.5 only
- 1
- Llama 4 Maverick only
- 25
- Like-for-like categories
- 8 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 18.1.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
GLM 4.5
GLM 4.5 leads, 12.8 against 9.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Llama 4 Maverick has a AA Agentic Index result, 0.6.
Directional only
Reasoning
GPQA Diamond
GLM 4.5
GLM 4.5 leads, 72.2% against 69.4%.
Same board, both measured
Math
AIME
GLM 4.5
GLM 4.5 leads, 86.7% against 25.2%.
Same board, both measured
Knowledge
MMLU Pro
GLM 4.5
GLM 4.5 leads, 81.2% against 79.4%.
Same board, both measured
Web design
Design Arena: websites
GLM 4.5
GLM 4.5 leads, 1170 against 871.
Same board, both measured
Long documents
Listed context window
Llama 4 Maverick
Llama 4 Maverick takes 524K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 4 Maverick
GLM 4.5 $0.0017, Llama 4 Maverick $0.0005 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Llama 4 Maverick has the number, $1.491.
Directional only
At a glance
- Coding index
- GLM 4.5 64.2 from 1 benchmark, Llama 4 Maverick 18.1 from 2 benchmarks.
- Widest category
- Web design, 35.0 points apart on average over 6 shared benchmarks.
- Widest single gap
- AIME: GLM 4.5 86.7% against Llama 4 Maverick 25.2%, 61.5 points apart on a 0 to 100 scale.
- Output price
- GLM 4.5 $2.20 against Llama 4 Maverick $0.6525 per million output tokens, 3.4x apart.
- Context window
- GLM 4.5 takes 131K tokens, Llama 4 Maverick 524K.
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 | GLM 4.5 | Bars | Llama 4 Maverick | Ties |
|---|---|---|---|---|
| Coding | 8 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 6 | 0 | ||
| Math | 6 | 1 | ||
| Knowledge | 9 | 1 | ||
| Web design | 6 | 0 | ||
| General | 20 | 0 | ||
| All shared boards | 57 | 2 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index80
| Benchmark | GLM 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 15.6% | Only Llama 4 Maverick measured |
| SWE-bench Verified | 64.2% | 21.0% | GLM 4.5 |
| AA Coding Index | Not measured | 16.3 | Only Llama 4 Maverick measured |
| LiveCodeBench (Vals AI) | 67.5% | 47.3% | GLM 4.5 |
| LiveCodeBench (Artificial Analysis run) | 73.8% | 39.7% | GLM 4.5 |
| SciCode | Not measured | 31.7% | Only Llama 4 Maverick measured |
| Terminal-Bench Hard (Artificial Analysis run) | 22.0% | 6.8% | GLM 4.5 |
| WeirdML | 40.6% | 24.5% | GLM 4.5 |
| ALE-Bench | 344.8 | 173.0 | GLM 4.5 |
| LMArena Text: coding | 1434 | 1301 | GLM 4.5 |
| LMArena Text: software and IT | 1440 | 1299 | 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 index10
| Benchmark | GLM 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.8 | 9.3 | GLM 4.5 |
| Epoch Capabilities Index | Not measured | 132.2 | Only Llama 4 Maverick measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GLM 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 0.6 | Only Llama 4 Maverick measured |
| τ²-Bench Telecom | 43.0% | 17.8% | 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 index60
| Benchmark | GLM 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| GPQA Diamond | 72.2% | 69.4% | GLM 4.5 |
| MMMU Pro (Vals AI) | Not measured | 71.7% | Only Llama 4 Maverick measured |
| GPQA Diamond (Artificial Analysis run) | 78.2% | 67.1% | GLM 4.5 |
| Humanity's Last Exam (Artificial Analysis run) | 13.0% | 4.9% | GLM 4.5 |
| ARC-AGI | Not measured | 4.4% | Only Llama 4 Maverick measured |
| ARC-AGI-2 | Not measured | 0.0% | Only Llama 4 Maverick measured |
| SimpleBench | Not measured | 27.7% | Only Llama 4 Maverick measured |
| LMArena Text: hard prompts | 1429 | 1281 | GLM 4.5 |
| LMArena Text: expert | 1433 | 1259 | GLM 4.5 |
| LMArena Text: hard prompts in English | 1429 | 1295 | GLM 4.5 |
| LMArena Vision: diagrams | Not measured | 1134 | Only Llama 4 Maverick measured |
| LMArena Vision: homework | Not measured | 1164 | Only Llama 4 Maverick measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index61
| Benchmark | GLM 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| AIME | 86.7% | 25.2% | GLM 4.5 |
| MATH 500 (Vals AI) | 94.0% | 85.2% | GLM 4.5 |
| MGSM (Vals AI) | 90.8% | 92.4% | Llama 4 Maverick |
| AA Math Index | 73.7 | 19.3 | GLM 4.5 |
| AIME 2025 (Artificial Analysis run) | 73.7% | 19.3% | GLM 4.5 |
| LMArena Text: math | 1427 | 1299 | GLM 4.5 |
| LMArena Text: mathematical work | 1430 | 1295 | GLM 4.5 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index91
| Benchmark | GLM 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| MMLU Pro | 81.2% | 79.4% | GLM 4.5 |
| LegalBench (Vals AI) | 75.6% | 77.8% | Llama 4 Maverick |
| CorpFin (Vals AI) | 61.0% | 49.7% | GLM 4.5 |
| TaxEval (Vals AI) | 72.4% | 66.6% | GLM 4.5 |
| MortgageTax (Vals AI) | Not measured | 58.5% | Only Llama 4 Maverick measured |
| MedQA (Vals AI) | 90.0% | 43.3% | GLM 4.5 |
| MedCode (Vals AI) | Not measured | 36.5% | Only Llama 4 Maverick measured |
| MMLU Pro (Artificial Analysis run) | 83.5% | 80.9% | GLM 4.5 |
| GeoBench | Not measured | 52.0% | Only Llama 4 Maverick measured |
| LMArena Text: science | 1444 | 1288 | GLM 4.5 |
| LMArena Text: medicine and healthcare | 1455 | 1275 | GLM 4.5 |
| LMArena Text: legal and government | 1438 | 1286 | GLM 4.5 |
| LMArena Text: business and finance | 1420 | 1260 | GLM 4.5 |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GLM 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| Design Arena: websites | 1170 | 871 | GLM 4.5 |
| Design Arena: UI components | 1144 | 899 | GLM 4.5 |
| Design Arena: game dev | 1145 | 838 | GLM 4.5 |
| Design Arena: data viz | 1159 | 882 | GLM 4.5 |
| Design Arena: 3D | 1170 | 901 | GLM 4.5 |
| Design Arena: all code categories | 1165 | 880 | GLM 4.5 |
| Design Arena: SVG | 1096 | Not measured | 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 index200
| Benchmark | GLM 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 35.7% | Only Llama 4 Maverick measured |
| MedScribe (Vals AI) | Not measured | 54.2% | Only Llama 4 Maverick measured |
| IFBench | 44.1% | 43.0% | GLM 4.5 |
| Long context reasoning (AA-LCR) | 52.7% | 50.0% | GLM 4.5 |
| DTBench | Not measured | 61.9% | Only Llama 4 Maverick measured |
| LMCA | Not measured | 15.9% | Only Llama 4 Maverick measured |
| Fiction.LiveBench | Not measured | 46.2% | Only Llama 4 Maverick measured |
| Creative writing (Lech Mazur) | 73.4% | 62.0% | GLM 4.5 |
| LMArena Text | 1430 | 1287 | GLM 4.5 |
| LMArena Text: instruction following | 1404 | 1267 | GLM 4.5 |
| LMArena Text: creative writing | 1395 | 1266 | GLM 4.5 |
| LMArena Vision | Not measured | 1142 | Only Llama 4 Maverick measured |
| LMArena Text: English | 1437 | 1303 | GLM 4.5 |
| LMArena Text: non-English | 1417 | 1269 | GLM 4.5 |
| LMArena Text: Chinese | 1465 | 1277 | GLM 4.5 |
| LMArena Text: German | 1407 | 1291 | GLM 4.5 |
| LMArena Text: Japanese | 1415 | 1206 | GLM 4.5 |
| LMArena Text: Korean | 1380 | 1203 | GLM 4.5 |
| LMArena Text: French | 1418 | 1259 | GLM 4.5 |
| LMArena Text: Spanish | 1454 | 1293 | GLM 4.5 |
| LMArena Text: Russian | 1413 | 1286 | GLM 4.5 |
| LMArena Text: Polish | 1422 | 1275 | GLM 4.5 |
| LMArena Text: multi-turn | 1415 | 1289 | GLM 4.5 |
| LMArena Text: longer queries | 1412 | 1280 | GLM 4.5 |
| LMArena Text: writing and language | 1403 | 1277 | GLM 4.5 |
| LMArena Text: entertainment and media | 1404 | 1250 | GLM 4.5 |
| LMArena Vision: English | Not measured | 1150 | Only Llama 4 Maverick measured |
| LMArena Vision: Chinese | Not measured | 1141 | Only Llama 4 Maverick measured |
| LMArena Vision: reading text | Not measured | 1143 | Only Llama 4 Maverick measured |
| LMArena Vision: humor | Not measured | 1100 | Only Llama 4 Maverick measured |
| LMArena Vision: creative writing | Not measured | 1099 | Only Llama 4 Maverick 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 | GLM 4.5 | Llama 4 Maverick | 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
Llama 4 Maverick costs less
Repository review
50K input + 3K output tokens
Llama 4 Maverick costs less
Agent loop
200K input + 10K output tokens
Llama 4 Maverick 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 | Z.ai GLM 4.5 | Meta Llama 4 Maverick |
|---|---|---|
| Maker | Z.ai | Meta Llama |
| Weights | Open weights | Open weights |
| Released | July 25, 2025 | April 5, 2025 |
| Context window | 131K | 524K |
| Input $/Mtok | $0.60 | $0.1875 |
| Output $/Mtok | $2.20 | $0.6525 |
| Coding index | 64.2 | 18.1 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | Not computable | $1.491 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 4.5 better than Llama 4 Maverick for coding?
Pick GLM 4.5 for coding: it scores 64.2 on the Vibe Coding Index against 18.1 for Llama 4 Maverick, though on 1 benchmark against 2. Pick Llama 4 Maverick when output tokens cost 3.4x less, or when the context window is larger, 524K against 131K tokens.
Which is cheaper, GLM 4.5 or Llama 4 Maverick?
GLM 4.5 costs $0.60 per million input tokens and $2.20 per million output tokens; Llama 4 Maverick costs $0.1875 and $0.6525. Cost per solved task is known for Llama 4 Maverick only.
Which has the bigger context window, GLM 4.5 or Llama 4 Maverick?
Llama 4 Maverick, with 524K tokens against 131K.
How many benchmarks is the GLM 4.5 vs Llama 4 Maverick comparison based on?
59 benchmarks have a result for both models as of October 21, 2026. GLM 4.5's coding index rests on 1 independent benchmark and Llama 4 Maverick's on 2. Where only one model has a result, the page says so instead of naming a winner.