Model comparison
GLM-4.5-Air vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
StepFunSummary
- They share 17 benchmarks with published results for both. GLM-4.5-Air scores higher in 1 category and Step 3.5 Flash in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 3.5 Flash leads 41.7 to 34.5.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.20 / $1.10 for GLM-4.5-Air.
- Step 3.5 Flash accepts more context: 256K tokens versus 131K.
Side by side
| GLM-4.5-Air | Step 3.5 Flash | |
|---|---|---|
| Provider | Z.ai (Zhipu) | StepFun |
| Noometry Index | 38.7 | 41.7 |
| Released | 2025-07-20 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 131K | 256K |
| Max output | 98K | 256K |
| Input $ / M tokens | $0.20 | $0.10 |
| Output $ / M tokens | $1.10 | $0.30 |
| Results tracked | 27 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
GLM-4.5-Air: 34.5 (#225), Step 3.5 Flash: 41.7 (#106)
| Benchmark | GLM-4.5-Air | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1397 | 1436 |
| GSO | 2.9% | — |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 23.3 (#166), Step 3.5 Flash: 21.2 (#202)
| Benchmark | GLM-4.5-Air | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1411 |
| Kagi LLM Benchmark | 43% | — |
| NYT Connections (extended) | — | 28.4% |
| ForecastBench | 59.2 | — |
Math Step 3.5 Flash leads
GLM-4.5-Air: 33.8 (#166), Step 3.5 Flash: 40.6 (#77)
| Benchmark | GLM-4.5-Air | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1396 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| Omni-MATH | 39.1% | — |
Knowledge Step 3.5 Flash leads
GLM-4.5-Air: 34.6 (#184), Step 3.5 Flash: 39.0 (#127)
| Benchmark | GLM-4.5-Air | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1370 | 1422 |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual Step 3.5 Flash leads
GLM-4.5-Air: 49.4 (#130), Step 3.5 Flash: 50.7 (#115)
| Benchmark | GLM-4.5-Air | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1366 | 1386 |
| LMArena Chinese | 1427 | 1448 |
| LMArena French | 1399 | 1421 |
| LMArena German | 1376 | 1404 |
| LMArena Japanese | 1348 | 1353 |
| LMArena Korean | 1306 | 1350 |
| LMArena Russian | 1373 | 1385 |
| LMArena Spanish | 1385 | 1419 |
Instruction Following Step 3.5 Flash leads
GLM-4.5-Air: 69.8 (#165), Step 3.5 Flash: 73.3 (#119)
| Benchmark | GLM-4.5-Air | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1353 | 1385 |
| IFEval | 81.2% | — |
Long Context Step 3.5 Flash leads
GLM-4.5-Air: 41.6 (#130), Step 3.5 Flash: 42.8 (#112)
| Benchmark | GLM-4.5-Air | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1367 | 1402 |
Writing & Preference Step 3.5 Flash leads
GLM-4.5-Air: 56.1 (#134), Step 3.5 Flash: 59.0 (#108)
| Benchmark | GLM-4.5-Air | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1384 | 1403 |
| LMArena Creative Writing | 1343 | 1357 |
| LMArena Multi-Turn | 1371 | 1405 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.7 on the Noometry Index.
Which is cheaper, GLM-4.5-Air 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-4.5-Air lists at $0.20 and $1.10.
Is GLM-4.5-Air or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Step 3.5 Flash does, with 256K tokens against 131K.
How many benchmarks do GLM-4.5-Air and Step 3.5 Flash share?
17 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Step 3.5 Flash has 19.