Model comparison
GLM-4.5V vs Step 3
GLM-4.5V and Step 3 score almost the same on the Noometry Index (39.8 vs 40.5), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. GLM-4.5V scores higher in 1 category and Step 3 in 8 categories; 5 gaps are clear of the uncertainty.
Side by side
| GLM-4.5V | Step 3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | StepFun |
| Noometry Index | 39.8 | 40.5 |
| Released | 2025-08-11 | — |
| Weights | Open | Open |
| Context window | 64K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $1.80 | — |
| Results tracked | 15 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.5V: 39.5 (#155), Step 3: 40.1 (#147)
| Benchmark | GLM-4.5V | Step 3 |
|---|---|---|
| LMArena Coding | 1347 | 1367 |
Reasoning Step 3 leads
GLM-4.5V: 27.4 (#119), Step 3: 28.4 (#105)
| Benchmark | GLM-4.5V | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 59.8% | 62.3% |
| LMArena Hard Prompts | 1334 | 1355 |
Math Too close to call
GLM-4.5V: 37.4 (#159), Step 3: 37.6 (#148)
| Benchmark | GLM-4.5V | Step 3 |
|---|---|---|
| LMArena Math | 1354 | 1366 |
Knowledge Too close to call
GLM-4.5V: 37.5 (#156), Step 3: 36.8 (#164)
| Benchmark | GLM-4.5V | Step 3 |
|---|---|---|
| LMArena Expert | 1353 | 1333 |
Multimodal Step 3 leads
GLM-4.5V: 34.3 (#92), Step 3: 35.5 (#86)
| Benchmark | GLM-4.5V | Step 3 |
|---|---|---|
| LMArena Vision | 1154 | 1177 |
Multilingual Step 3 leads
GLM-4.5V: 44.6 (#177), Step 3: 46.3 (#159)
| Benchmark | GLM-4.5V | Step 3 |
|---|---|---|
| LMArena Non-English | 1303 | 1327 |
| LMArena Chinese | 1337 | 1397 |
| LMArena Russian | 1298 | 1331 |
| LMArena Spanish | 1336 | 1371 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
Instruction Following Step 3 leads
GLM-4.5V: 69.2 (#175), Step 3: 70.4 (#164)
| Benchmark | GLM-4.5V | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1311 | 1332 |
Long Context Too close to call
GLM-4.5V: 39.6 (#171), Step 3: 40.3 (#157)
| Benchmark | GLM-4.5V | Step 3 |
|---|---|---|
| LMArena Longer Query | 1304 | 1326 |
Writing & Preference Step 3 leads
GLM-4.5V: 52.5 (#170), Step 3: 54.3 (#151)
| Benchmark | GLM-4.5V | Step 3 |
|---|---|---|
| LMArena Text | 1333 | 1350 |
| LMArena Creative Writing | 1295 | 1321 |
| LMArena Multi-Turn | 1332 | 1341 |
Frequently asked questions
Is GLM-4.5V better than Step 3?
GLM-4.5V and Step 3 score almost the same on the Noometry Index (39.8 vs 40.5), so choose on price, context window or the category you care about most.
Is GLM-4.5V or Step 3 better for coding?
They score almost the same on coding (39.5 vs 40.1); test both on your own repository before choosing.
How many benchmarks do GLM-4.5V and Step 3 share?
15 benchmarks have published results for both models. GLM-4.5V has 15 scored results on Noometry and Step 3 has 17.