Model comparison
GLM-5.3-Flash vs Step 3
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 40.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
StepFunSummary
- They share 16 benchmarks with published results for both. GLM-5.3-Flash scores higher in 9 categories and Step 3 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.3-Flash leads 58.4 to 36.8.
Side by side
| GLM-5.3-Flash | Step 3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | StepFun |
| Noometry Index | 51.8 | 40.5 |
| Released | 2026-08-20 | — |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.50 | — |
| Results tracked | 40 | 17 |
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), Step 3: 40.1 (#147)
| Benchmark | GLM-5.3-Flash | Step 3 |
|---|---|---|
| LMArena Coding | 1508 | 1367 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| CursorBench | 36.8% | — |
| LMArena WebDev | 1609 | — |
| FrontierSWE | 18.1% | — |
| SciCode | 51.6% | — |
| ALE-Bench | 303.55 | — |
Agentic & Tool Use Not comparable
GLM-5.3-Flash: 34.2 (#47), Step 3: —
| Benchmark | GLM-5.3-Flash | Step 3 |
|---|---|---|
| APEX-Agents | 52.8% | — |
| GDP.pdf | 14% | — |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 48.0 (#42), Step 3: 28.4 (#105)
| Benchmark | GLM-5.3-Flash | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1491 | 1355 |
| ARC-AGI-2 | 65.8% | — |
| Kagi LLM Benchmark | — | 62.3% |
| ARC-AGI-1 | 91% | — |
| CritPt | 15.4% | — |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
| Epoch Capabilities Index | 151.88 | — |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.3 (#47), Step 3: 37.6 (#148)
| Benchmark | GLM-5.3-Flash | Step 3 |
|---|---|---|
| LMArena Math | 1500 | 1366 |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 93.9% | — |
| ProofBench | 21% | — |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#36), Step 3: 36.8 (#164)
| Benchmark | GLM-5.3-Flash | Step 3 |
|---|---|---|
| LMArena Expert | 1513 | 1333 |
| GPQA Diamond | 90.2% | — |
Multimodal GLM-5.3-Flash leads
GLM-5.3-Flash: 42.8 (#27), Step 3: 35.5 (#86)
| Benchmark | GLM-5.3-Flash | Step 3 |
|---|---|---|
| LMArena Vision | 1296 | 1177 |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.0 (#25), Step 3: 46.3 (#159)
| Benchmark | GLM-5.3-Flash | Step 3 |
|---|---|---|
| LMArena Non-English | 1462 | 1327 |
| LMArena Chinese | 1527 | 1397 |
| LMArena German | 1470 | 1371 |
| LMArena Korean | 1446 | 1269 |
| LMArena Russian | 1469 | 1331 |
| LMArena Spanish | 1471 | 1371 |
| LMArena French | 1496 | — |
| LMArena Japanese | 1429 | — |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.5 (#20), Step 3: 70.4 (#164)
| Benchmark | GLM-5.3-Flash | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1478 | 1332 |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.4 (#39), Step 3: 40.3 (#157)
| Benchmark | GLM-5.3-Flash | Step 3 |
|---|---|---|
| LMArena Longer Query | 1482 | 1326 |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.3 (#50), Step 3: 54.3 (#151)
| Benchmark | GLM-5.3-Flash | Step 3 |
|---|---|---|
| LMArena Text | 1471 | 1350 |
| LMArena Creative Writing | 1442 | 1321 |
| LMArena Multi-Turn | 1467 | 1341 |
Frequently asked questions
Is GLM-5.3-Flash better than Step 3?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 40.5 on the Noometry Index.
Is GLM-5.3-Flash or Step 3 better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 40.1 in the Noometry coding category.
How many benchmarks do GLM-5.3-Flash and Step 3 share?
16 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and Step 3 has 17.