Model comparison
GLM-5 vs Step 3
GLM-5 is the stronger model overall, scoring 46.1 to 40.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
StepFunSummary
- They share 16 benchmarks with published results for both. GLM-5 scores higher in 7 categories and Step 3 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 36.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for GLM-5 and 62.3% for Step 3.
Side by side
| GLM-5 | Step 3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | StepFun |
| Noometry Index | 46.1 | 40.5 |
| Released | 2026-02-11 | — |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 45 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Step 3: 40.1 (#147)
| Benchmark | GLM-5 | Step 3 |
|---|---|---|
| LMArena Coding | 1461 | 1367 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), Step 3: —
| Benchmark | GLM-5 | Step 3 |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning Too close to call
GLM-5: 27.6 (#116), Step 3: 28.4 (#105)
| Benchmark | GLM-5 | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 75% | 62.3% |
| LMArena Hard Prompts | 1452 | 1355 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| Chess Puzzles | 10% | — |
| Epoch Capabilities Index | 145.83 | — |
| ForecastBench | 61 | — |
Math GLM-5 leads
GLM-5: 46.4 (#71), Step 3: 37.6 (#148)
| Benchmark | GLM-5 | Step 3 |
|---|---|---|
| LMArena Math | 1440 | 1366 |
| MathArena Final-Answer Competitions | 65.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), Step 3: 36.8 (#164)
| Benchmark | GLM-5 | Step 3 |
|---|---|---|
| LMArena Expert | 1454 | 1333 |
| GPQA Diamond | 87.8% | — |
| Vectara Hallucination Rate | 10.1% | — |
Multimodal Not comparable
GLM-5: —, Step 3: 35.5 (#86)
| Benchmark | GLM-5 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), Step 3: 46.3 (#159)
| Benchmark | GLM-5 | Step 3 |
|---|---|---|
| LMArena Non-English | 1430 | 1327 |
| LMArena Chinese | 1511 | 1397 |
| LMArena German | 1445 | 1371 |
| LMArena Korean | 1423 | 1269 |
| LMArena Russian | 1436 | 1331 |
| LMArena Spanish | 1454 | 1371 |
| LMArena French | 1455 | — |
| LMArena Japanese | 1416 | — |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), Step 3: 70.4 (#164)
| Benchmark | GLM-5 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1428 | 1332 |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), Step 3: 40.3 (#157)
| Benchmark | GLM-5 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1446 | 1326 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Step 3: 54.3 (#151)
| Benchmark | GLM-5 | Step 3 |
|---|---|---|
| LMArena Text | 1446 | 1350 |
| LMArena Creative Writing | 1439 | 1321 |
| LMArena Multi-Turn | 1456 | 1341 |
| EQ-Bench Creative Writing | 1601 | — |
Frequently asked questions
Is GLM-5 better than Step 3?
GLM-5 is the stronger model overall, scoring 46.1 to 40.5 on the Noometry Index.
Is GLM-5 or Step 3 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 40.1 in the Noometry coding category.
How many benchmarks do GLM-5 and Step 3 share?
16 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Step 3 has 17.