Model comparison
GLM-5 vs Llama 4 Maverick
GLM-5 is the stronger model overall, scoring 46.1 to 30.9 on the Noometry Index. Llama 4 Maverick costs 5.1× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
MetaSummary
- They share 32 benchmarks with published results for both. GLM-5 scores higher in 9 categories and Llama 4 Maverick in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5 leads 66.0 to 38.8.
- The biggest single-benchmark swing is NYT Connections (extended): 74.8% for GLM-5 and 8% for Llama 4 Maverick.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $1 / $3.20 for GLM-5.
- GLM-5 accepts more context: 205K tokens versus 128K.
Side by side
| GLM-5 | Llama 4 Maverick | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 46.1 | 30.9 |
| Released | 2026-02-11 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 205K | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $1 | $0.19 |
| Output $ / M tokens | $3.20 | $0.65 |
| Results tracked | 45 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Llama 4 Maverick: 26.6 (#324)
| Benchmark | GLM-5 | Llama 4 Maverick |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | 21% |
| WeirdML | 48.2% | 24.5% |
| LMArena Coding | 1461 | 1302 |
| ALE-Bench | 765.62 | 172.97 |
| SWE-bench Verified | 72.1% | — |
| Aider Polyglot | — | 15.6% |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 33.1% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
Agentic & Tool Use GLM-5 leads
GLM-5: 31.1 (#71), Llama 4 Maverick: 28.2 (#91)
| Benchmark | GLM-5 | Llama 4 Maverick |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| Berkeley Function Calling Leaderboard | — | 37.3% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#116), Llama 4 Maverick: 10.1 (#342)
| Benchmark | GLM-5 | Llama 4 Maverick |
|---|---|---|
| ARC-AGI-2 | 4.9% | 0% |
| SimpleBench | 53.2% | 27.7% |
| Kagi LLM Benchmark | 75% | 55.9% |
| NYT Connections (extended) | 74.8% | 8% |
| ARC-AGI-1 | 44.7% | 4.4% |
| LMArena Hard Prompts | 1452 | 1281 |
| Epoch Capabilities Index | 145.83 | 132.2 |
| ForecastBench | 61 | 57.5 |
| CritPt | — | 0% |
| Chess Puzzles | 10% | — |
| EnigmaEval | — | 0.6% |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
Math GLM-5 leads
GLM-5: 46.4 (#71), Llama 4 Maverick: 26.0 (#262)
| Benchmark | GLM-5 | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 20.6% |
| LMArena Math | 1440 | 1299 |
| FrontierMath (Feb 2025 set) | 16.4% | 0.7% |
| MathArena Final-Answer Competitions | 65.7% | — |
| Omni-MATH | — | 42.2% |
| MATH Level 5 | — | 73% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), Llama 4 Maverick: 33.4 (#204)
| Benchmark | GLM-5 | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 87.8% | 67% |
| Vectara Hallucination Rate | 10.1% | 8.2% |
| LMArena Expert | 1454 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| GPQA (HELM) | — | 65% |
Multimodal Not comparable
GLM-5: —, Llama 4 Maverick: 31.6 (#105)
| Benchmark | GLM-5 | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), Llama 4 Maverick: 42.2 (#195)
| Benchmark | GLM-5 | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1430 | 1269 |
| LMArena Chinese | 1511 | 1277 |
| LMArena French | 1455 | 1259 |
| LMArena German | 1445 | 1291 |
| LMArena Japanese | 1416 | 1207 |
| LMArena Korean | 1423 | 1203 |
| LMArena Russian | 1436 | 1286 |
| LMArena Spanish | 1454 | 1293 |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), Llama 4 Maverick: 71.7 (#146)
| Benchmark | GLM-5 | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1428 | 1267 |
| IFEval | — | 90.8% |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), Llama 4 Maverick: 31.4 (#279)
| Benchmark | GLM-5 | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1446 | 1280 |
| Fiction.LiveBench | — | 46.2% |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Llama 4 Maverick: 38.8 (#252)
| Benchmark | GLM-5 | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1446 | 1287 |
| LMArena Creative Writing | 1439 | 1267 |
| EQ-Bench Creative Writing | 1601 | 860 |
| LMArena Multi-Turn | 1456 | 1289 |
| Short-Story Creative Writing | — | 62% |
| WildBench | — | 80% |
Frequently asked questions
Is GLM-5 better than Llama 4 Maverick?
GLM-5 is the stronger model overall, scoring 46.1 to 30.9 on the Noometry Index. Llama 4 Maverick costs 5.1× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Which is cheaper, GLM-5 or Llama 4 Maverick?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; GLM-5 lists at $1 and $3.20.
Is GLM-5 or Llama 4 Maverick better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 128K.
How many benchmarks do GLM-5 and Llama 4 Maverick share?
32 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Llama 4 Maverick has 54.