Model comparison
GLM-5.3-Flash vs Llama 3.1-405B
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 30.7 on the Noometry Index.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. GLM-5.3-Flash scores higher in 9 categories and Llama 3.1-405B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.3-Flash leads 53.3 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.9% for GLM-5.3-Flash and 9.7% for Llama 3.1-405B.
Side by side
| GLM-5.3-Flash | Llama 3.1-405B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 51.8 | 30.7 |
| Released | 2026-08-20 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.50 | — |
| Results tracked | 40 | 42 |
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 3.1-405B: 33.1 (#262)
| Benchmark | GLM-5.3-Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1508 | 1291 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| CursorBench | 36.8% | — |
| LMArena WebDev | 1609 | — |
| FrontierSWE | 18.1% | — |
| SciCode | 51.6% | — |
| WeirdML | — | 21.4% |
| ALE-Bench | 303.55 | — |
Agentic & Tool Use GLM-5.3-Flash leads
GLM-5.3-Flash: 34.2 (#47), Llama 3.1-405B: 21.0 (#140)
| Benchmark | GLM-5.3-Flash | Llama 3.1-405B |
|---|---|---|
| APEX-Agents | 52.8% | — |
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
| GDP.pdf | 14% | — |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 48.0 (#42), Llama 3.1-405B: 16.8 (#300)
| Benchmark | GLM-5.3-Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 1491 | 1269 |
| Epoch Capabilities Index | 151.88 | 128.75 |
| ARC-AGI-2 | 65.8% | — |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| ARC-AGI-1 | 91% | — |
| CritPt | 15.4% | — |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | — | 61.4% |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
| BIG-Bench Hard | — | 82.9% |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.3 (#47), Llama 3.1-405B: 18.4 (#290)
| Benchmark | GLM-5.3-Flash | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.9% | 9.7% |
| LMArena Math | 1500 | 1281 |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 21% | — |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#36), Llama 3.1-405B: 30.4 (#227)
| Benchmark | GLM-5.3-Flash | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 90.2% | 50.9% |
| LMArena Expert | 1513 | 1243 |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
GLM-5.3-Flash: 42.8 (#27), Llama 3.1-405B: —
| Benchmark | GLM-5.3-Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1296 | — |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.0 (#25), Llama 3.1-405B: 40.7 (#214)
| Benchmark | GLM-5.3-Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1462 | 1248 |
| LMArena Chinese | 1527 | 1242 |
| LMArena French | 1496 | 1279 |
| LMArena German | 1470 | 1252 |
| LMArena Japanese | 1429 | 1208 |
| LMArena Korean | 1446 | 1184 |
| LMArena Russian | 1469 | 1265 |
| LMArena Spanish | 1471 | 1260 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.5 (#20), Llama 3.1-405B: 65.9 (#214)
| Benchmark | GLM-5.3-Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1478 | 1259 |
| IFEval | — | 81.1% |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.4 (#39), Llama 3.1-405B: 38.4 (#197)
| Benchmark | GLM-5.3-Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1482 | 1266 |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.3 (#50), Llama 3.1-405B: 38.9 (#251)
| Benchmark | GLM-5.3-Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1471 | 1284 |
| LMArena Creative Writing | 1442 | 1262 |
| LMArena Multi-Turn | 1467 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
Frequently asked questions
Is GLM-5.3-Flash better than Llama 3.1-405B?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 30.7 on the Noometry Index.
Is GLM-5.3-Flash or Llama 3.1-405B better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 33.1 in the Noometry coding category.
How many benchmarks do GLM-5.3-Flash and Llama 3.1-405B share?
20 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and Llama 3.1-405B has 42.