Model comparison
GLM-4.6 vs Llama 4 Maverick
GLM-4.6 is the stronger model overall, scoring 41.4 to 30.9 on the Noometry Index. Llama 4 Maverick costs 3.3× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
MetaSummary
- They share 26 benchmarks with published results for both. GLM-4.6 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-4.6 leads 61.1 to 38.8.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 72.4% for GLM-4.6 and 37.3% for Llama 4 Maverick.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- GLM-4.6 accepts more context: 205K tokens versus 128K.
Side by side
| GLM-4.6 | Llama 4 Maverick | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 41.4 | 30.9 |
| Released | 2025-09-30 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 205K | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $0.60 | $0.19 |
| Output $ / M tokens | $2.20 | $0.65 |
| Results tracked | 29 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 40.1 (#148), Llama 4 Maverick: 26.6 (#324)
| Benchmark | GLM-4.6 | Llama 4 Maverick |
|---|---|---|
| SWE-bench Verified (bash only) | 55.4% | 21% |
| SciCode | 38.4% | 33.1% |
| LMArena Coding | 1449 | 1302 |
| ALE-Bench | 340.82 | 172.97 |
| Aider Polyglot | — | 15.6% |
| LMArena WebDev | 1340 | — |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.3 (#66), Llama 4 Maverick: 28.2 (#91)
| Benchmark | GLM-4.6 | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | 72.4% | 37.3% |
| Terminal-Bench | 24.5% | — |
Reasoning GLM-4.6 leads
GLM-4.6: 23.7 (#172), Llama 4 Maverick: 10.1 (#342)
| Benchmark | GLM-4.6 | Llama 4 Maverick |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 55.9% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1440 | 1281 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| EnigmaEval | — | 0.6% |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
| Epoch Capabilities Index | — | 132.2 |
| ForecastBench | — | 57.5 |
Math GLM-4.6 leads
GLM-4.6: 39.1 (#111), Llama 4 Maverick: 26.0 (#262)
| Benchmark | GLM-4.6 | Llama 4 Maverick |
|---|---|---|
| LMArena Math | 1432 | 1299 |
| FrontierMath (Feb 2025 set) | 3.8% | 0.7% |
| OTIS Mock AIME 2024-2025 | — | 20.6% |
| Omni-MATH | — | 42.2% |
| MATH Level 5 | — | 73% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-4.6 leads
GLM-4.6: 40.2 (#124), Llama 4 Maverick: 33.4 (#204)
| Benchmark | GLM-4.6 | Llama 4 Maverick |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 8.2% |
| LMArena Expert | 1431 | 1259 |
| GPQA Diamond | — | 67% |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| GPQA (HELM) | — | 65% |
Multimodal Not comparable
GLM-4.6: —, Llama 4 Maverick: 31.6 (#105)
| Benchmark | GLM-4.6 | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual GLM-4.6 leads
GLM-4.6: 53.5 (#66), Llama 4 Maverick: 42.2 (#195)
| Benchmark | GLM-4.6 | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1426 | 1269 |
| LMArena Chinese | 1499 | 1277 |
| LMArena French | 1459 | 1259 |
| LMArena German | 1447 | 1291 |
| LMArena Japanese | 1393 | 1207 |
| LMArena Korean | 1400 | 1203 |
| LMArena Russian | 1419 | 1286 |
| LMArena Spanish | 1436 | 1293 |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.3 (#98), Llama 4 Maverick: 71.7 (#146)
| Benchmark | GLM-4.6 | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1410 | 1267 |
| IFEval | — | 90.8% |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#94), Llama 4 Maverick: 31.4 (#279)
| Benchmark | GLM-4.6 | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1422 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.1 (#90), Llama 4 Maverick: 38.8 (#252)
| Benchmark | GLM-4.6 | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1440 | 1287 |
| LMArena Creative Writing | 1411 | 1267 |
| EQ-Bench Creative Writing | 1411 | 860 |
| LMArena Multi-Turn | 1427 | 1289 |
| Short-Story Creative Writing | — | 62% |
| WildBench | — | 80% |
Frequently asked questions
Is GLM-4.6 better than Llama 4 Maverick?
GLM-4.6 is the stronger model overall, scoring 41.4 to 30.9 on the Noometry Index. Llama 4 Maverick costs 3.3× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6 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-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or Llama 4 Maverick better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 128K.
How many benchmarks do GLM-4.6 and Llama 4 Maverick share?
26 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Llama 4 Maverick has 54.