Model comparison
GLM-4.6 vs Step 3
GLM-4.6 and Step 3 score almost the same on the Noometry Index (41.4 vs 40.5), so choose on price, context window or the category you care about most.
Last verified . 16 shared benchmarks.
StepFunSummary
- They share 16 benchmarks with published results for both. GLM-4.6 scores higher in 6 categories and Step 3 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.6 leads 53.5 to 46.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 47.4% for GLM-4.6 and 62.3% for Step 3.
Side by side
| GLM-4.6 | Step 3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | StepFun |
| Noometry Index | 41.4 | 40.5 |
| Released | 2025-09-30 | — |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 29 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.6: 40.1 (#148), Step 3: 40.1 (#147)
| Benchmark | GLM-4.6 | Step 3 |
|---|---|---|
| LMArena Coding | 1449 | 1367 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use Not comparable
GLM-4.6: 32.3 (#66), Step 3: —
| Benchmark | GLM-4.6 | Step 3 |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning Step 3 leads
GLM-4.6: 23.7 (#172), Step 3: 28.4 (#105)
| Benchmark | GLM-4.6 | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 62.3% |
| LMArena Hard Prompts | 1440 | 1355 |
| CritPt | 1.1% | — |
Math GLM-4.6 leads
GLM-4.6: 39.1 (#111), Step 3: 37.6 (#148)
| Benchmark | GLM-4.6 | Step 3 |
|---|---|---|
| LMArena Math | 1432 | 1366 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-4.6 leads
GLM-4.6: 40.2 (#124), Step 3: 36.8 (#164)
| Benchmark | GLM-4.6 | Step 3 |
|---|---|---|
| LMArena Expert | 1431 | 1333 |
| Vectara Hallucination Rate | 9.5% | — |
Multimodal Not comparable
GLM-4.6: —, Step 3: 35.5 (#86)
| Benchmark | GLM-4.6 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual GLM-4.6 leads
GLM-4.6: 53.5 (#66), Step 3: 46.3 (#159)
| Benchmark | GLM-4.6 | Step 3 |
|---|---|---|
| LMArena Non-English | 1426 | 1327 |
| LMArena Chinese | 1499 | 1397 |
| LMArena German | 1447 | 1371 |
| LMArena Korean | 1400 | 1269 |
| LMArena Russian | 1419 | 1331 |
| LMArena Spanish | 1436 | 1371 |
| LMArena French | 1459 | — |
| LMArena Japanese | 1393 | — |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.3 (#98), Step 3: 70.4 (#164)
| Benchmark | GLM-4.6 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1332 |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#94), Step 3: 40.3 (#157)
| Benchmark | GLM-4.6 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1422 | 1326 |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.1 (#90), Step 3: 54.3 (#151)
| Benchmark | GLM-4.6 | Step 3 |
|---|---|---|
| LMArena Text | 1440 | 1350 |
| LMArena Creative Writing | 1411 | 1321 |
| LMArena Multi-Turn | 1427 | 1341 |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Step 3?
GLM-4.6 and Step 3 score almost the same on the Noometry Index (41.4 vs 40.5), so choose on price, context window or the category you care about most.
Is GLM-4.6 or Step 3 better for coding?
They score almost the same on coding (40.1 vs 40.1); test both on your own repository before choosing.
How many benchmarks do GLM-4.6 and Step 3 share?
16 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Step 3 has 17.