Model comparison
GLM-4.7-Flash vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 38.8 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. GLM-4.7-Flash scores higher in 3 categories and Step 3 in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3 leads 28.4 to 20.9.
Side by side
| GLM-4.7-Flash | Step 3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | StepFun |
| Noometry Index | 38.8 | 40.5 |
| Released | 2026-01-19 | — |
| Weights | Open | Open |
| Context window | 200K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 21 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.7-Flash: 40.6 (#135), Step 3: 40.1 (#147)
| Benchmark | GLM-4.7-Flash | Step 3 |
|---|---|---|
| LMArena Coding | 1383 | 1367 |
Reasoning Step 3 leads
GLM-4.7-Flash: 20.9 (#229), Step 3: 28.4 (#105)
| Benchmark | GLM-4.7-Flash | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1356 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 0% | — |
Math Step 3 leads
GLM-4.7-Flash: 36.1 (#173), Step 3: 37.6 (#148)
| Benchmark | GLM-4.7-Flash | Step 3 |
|---|---|---|
| LMArena Math | 1355 | 1366 |
| OTIS Mock AIME 2024-2025 | 58.3% | — |
Knowledge Step 3 leads
GLM-4.7-Flash: 35.5 (#184), Step 3: 36.8 (#164)
| Benchmark | GLM-4.7-Flash | Step 3 |
|---|---|---|
| LMArena Expert | 1357 | 1333 |
| GPQA Diamond | 60.5% | — |
| Vectara Hallucination Rate | 9.3% | — |
Multimodal Not comparable
GLM-4.7-Flash: —, Step 3: 35.5 (#86)
| Benchmark | GLM-4.7-Flash | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Too close to call
GLM-4.7-Flash: 46.5 (#158), Step 3: 46.3 (#159)
| Benchmark | GLM-4.7-Flash | Step 3 |
|---|---|---|
| LMArena Non-English | 1330 | 1327 |
| LMArena Chinese | 1403 | 1397 |
| LMArena German | 1337 | 1371 |
| LMArena Korean | 1283 | 1269 |
| LMArena Russian | 1332 | 1331 |
| LMArena Spanish | 1350 | 1371 |
| LMArena French | 1332 | — |
Instruction Following Too close to call
GLM-4.7-Flash: 70.1 (#167), Step 3: 70.4 (#164)
| Benchmark | GLM-4.7-Flash | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1327 | 1332 |
Long Context Too close to call
GLM-4.7-Flash: 40.9 (#148), Step 3: 40.3 (#157)
| Benchmark | GLM-4.7-Flash | Step 3 |
|---|---|---|
| LMArena Longer Query | 1345 | 1326 |
Writing & Preference Step 3 leads
GLM-4.7-Flash: 47.4 (#210), Step 3: 54.3 (#151)
| Benchmark | GLM-4.7-Flash | Step 3 |
|---|---|---|
| LMArena Text | 1351 | 1350 |
| LMArena Creative Writing | 1297 | 1321 |
| LMArena Multi-Turn | 1342 | 1341 |
| EQ-Bench Creative Writing | 1125 | — |
Frequently asked questions
Is GLM-4.7-Flash better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 38.8 on the Noometry Index.
Is GLM-4.7-Flash or Step 3 better for coding?
They score almost the same on coding (40.6 vs 40.1); test both on your own repository before choosing.
How many benchmarks do GLM-4.7-Flash and Step 3 share?
15 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Step 3 has 17.