Model comparison
GLM-5 vs Step 3.5 Flash
GLM-5 is the stronger model overall, scoring 45.9 to 41.7 on the Noometry Index. Step 3.5 Flash costs 10× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
StepFunSummary
- They share 19 benchmarks with published results for both. GLM-5 scores higher in 8 categories and Step 3.5 Flash in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.2 to 39.0.
- The biggest single-benchmark swing is NYT Connections (extended): 74.8% for GLM-5 and 28.4% for Step 3.5 Flash.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $1 / $3.20 for GLM-5.
- Step 3.5 Flash accepts more context: 256K tokens versus 205K.
Side by side
| GLM-5 | Step 3.5 Flash | |
|---|---|---|
| Provider | Z.ai (Zhipu) | StepFun |
| Noometry Index | 45.9 | 41.7 |
| Released | 2026-02-11 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 205K | 256K |
| Max output | 131K | 256K |
| Input $ / M tokens | $1 | $0.10 |
| Output $ / M tokens | $3.20 | $0.30 |
| Results tracked | 45 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#47), Step 3.5 Flash: 41.7 (#106)
| Benchmark | GLM-5 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1461 | 1436 |
| 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: 30.9 (#65), Step 3.5 Flash: —
| Benchmark | GLM-5 | Step 3.5 Flash |
|---|---|---|
| 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 GLM-5 leads
GLM-5: 27.6 (#100), Step 3.5 Flash: 21.2 (#202)
| Benchmark | GLM-5 | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 74.8% | 28.4% |
| LMArena Hard Prompts | 1451 | 1411 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 44.7% | — |
| Chess Puzzles | 10% | — |
| Epoch Capabilities Index | 145.84 | — |
| ForecastBench | 61 | — |
Math GLM-5 leads
GLM-5: 44.8 (#66), Step 3.5 Flash: 40.6 (#77)
| Benchmark | GLM-5 | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | 65.7% | 66.8% |
| LMArena Math | 1440 | 1408 |
| OTIS Mock AIME 2024-2025 | 80% | — |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.2 (#59), Step 3.5 Flash: 39.0 (#127)
| Benchmark | GLM-5 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1454 | 1422 |
| GPQA Diamond | 87.8% | — |
| Vectara Hallucination Rate | 10.1% | — |
Multilingual GLM-5 leads
GLM-5: 53.9 (#57), Step 3.5 Flash: 50.7 (#115)
| Benchmark | GLM-5 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1430 | 1386 |
| LMArena Chinese | 1511 | 1448 |
| LMArena French | 1455 | 1421 |
| LMArena German | 1445 | 1404 |
| LMArena Japanese | 1416 | 1353 |
| LMArena Korean | 1421 | 1350 |
| LMArena Russian | 1436 | 1385 |
| LMArena Spanish | 1452 | 1419 |
Instruction Following GLM-5 leads
GLM-5: 75.4 (#64), Step 3.5 Flash: 73.3 (#119)
| Benchmark | GLM-5 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1427 | 1385 |
Long Context GLM-5 leads
GLM-5: 44.6 (#58), Step 3.5 Flash: 42.8 (#112)
| Benchmark | GLM-5 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1446 | 1402 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.2 (#38), Step 3.5 Flash: 59.0 (#108)
| Benchmark | GLM-5 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1446 | 1403 |
| LMArena Creative Writing | 1438 | 1357 |
| LMArena Multi-Turn | 1456 | 1405 |
| EQ-Bench Creative Writing | 1601 | — |
Frequently asked questions
Is GLM-5 better than Step 3.5 Flash?
GLM-5 is the stronger model overall, scoring 45.9 to 41.7 on the Noometry Index. Step 3.5 Flash costs 10× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Which is cheaper, GLM-5 or Step 3.5 Flash?
Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; GLM-5 lists at $1 and $3.20.
Is GLM-5 or Step 3.5 Flash better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 41.7 in the Noometry coding category.
Which has the bigger context window?
Step 3.5 Flash does, with 256K tokens against 205K.
How many benchmarks do GLM-5 and Step 3.5 Flash share?
19 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Step 3.5 Flash has 19.