Model comparison
GLM-5.3-Flash vs Llama 4 Maverick
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 30.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
MetaSummary
- They share 26 benchmarks with published results for both. GLM-5.3-Flash scores higher in 10 categories and Llama 4 Maverick in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.3-Flash leads 48.0 to 10.1.
- The biggest single-benchmark swing is ARC-AGI-1: 91% for GLM-5.3-Flash and 4.4% for Llama 4 Maverick.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $0.19 / $0.65 for Llama 4 Maverick.
- GLM-5.3-Flash accepts more context: 1M tokens versus 128K.
Side by side
| GLM-5.3-Flash | Llama 4 Maverick | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 51.8 | 30.9 |
| Released | 2026-08-20 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 1M | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $0.15 | $0.19 |
| Output $ / M tokens | $0.50 | $0.65 |
| Results tracked | 40 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
GLM-5.3-Flash: 53.1 (#31), Llama 4 Maverick: 26.6 (#324)
| Benchmark | GLM-5.3-Flash | Llama 4 Maverick |
|---|---|---|
| SciCode | 51.6% | 33.1% |
| LMArena Coding | 1508 | 1302 |
| ALE-Bench | 303.55 | 172.97 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| CursorBench | 36.8% | — |
| LMArena WebDev | 1609 | — |
| FrontierSWE | 18.1% | — |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
Agentic & Tool Use GLM-5.3-Flash leads
GLM-5.3-Flash: 34.2 (#47), Llama 4 Maverick: 28.2 (#91)
| Benchmark | GLM-5.3-Flash | Llama 4 Maverick |
|---|---|---|
| APEX-Agents | 52.8% | — |
| Berkeley Function Calling Leaderboard | — | 37.3% |
| GDP.pdf | 14% | — |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 48.0 (#42), Llama 4 Maverick: 10.1 (#342)
| Benchmark | GLM-5.3-Flash | Llama 4 Maverick |
|---|---|---|
| ARC-AGI-2 | 65.8% | 0% |
| ARC-AGI-1 | 91% | 4.4% |
| CritPt | 15.4% | 0% |
| LMArena Hard Prompts | 1491 | 1281 |
| Epoch Capabilities Index | 151.88 | 132.2 |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| Chess Puzzles | 14% | — |
| EnigmaEval | — | 0.6% |
| Mystery Game Puzzles | 8% | — |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
| ForecastBench | — | 57.5 |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.3 (#47), Llama 4 Maverick: 26.0 (#262)
| Benchmark | GLM-5.3-Flash | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.9% | 20.6% |
| LMArena Math | 1500 | 1299 |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 21% | — |
| Omni-MATH | — | 42.2% |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#36), Llama 4 Maverick: 33.4 (#204)
| Benchmark | GLM-5.3-Flash | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 90.2% | 67% |
| LMArena Expert | 1513 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |
Multimodal GLM-5.3-Flash leads
GLM-5.3-Flash: 42.8 (#27), Llama 4 Maverick: 31.6 (#105)
| Benchmark | GLM-5.3-Flash | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1296 | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.0 (#25), Llama 4 Maverick: 42.2 (#195)
| Benchmark | GLM-5.3-Flash | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1462 | 1269 |
| LMArena Chinese | 1527 | 1277 |
| LMArena French | 1496 | 1259 |
| LMArena German | 1470 | 1291 |
| LMArena Japanese | 1429 | 1207 |
| LMArena Korean | 1446 | 1203 |
| LMArena Russian | 1469 | 1286 |
| LMArena Spanish | 1471 | 1293 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.5 (#20), Llama 4 Maverick: 71.7 (#146)
| Benchmark | GLM-5.3-Flash | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1478 | 1267 |
| IFEval | — | 90.8% |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.4 (#39), Llama 4 Maverick: 31.4 (#279)
| Benchmark | GLM-5.3-Flash | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1482 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.3 (#50), Llama 4 Maverick: 38.8 (#252)
| Benchmark | GLM-5.3-Flash | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1471 | 1287 |
| LMArena Creative Writing | 1442 | 1267 |
| LMArena Multi-Turn | 1467 | 1289 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
| WildBench | — | 80% |
Frequently asked questions
Is GLM-5.3-Flash better than Llama 4 Maverick?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 30.9 on the Noometry Index.
Which is cheaper, GLM-5.3-Flash or Llama 4 Maverick?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Llama 4 Maverick lists at $0.19 and $0.65.
Is GLM-5.3-Flash or Llama 4 Maverick better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 128K.
How many benchmarks do GLM-5.3-Flash and Llama 4 Maverick share?
26 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and Llama 4 Maverick has 54.