GLM-4.7-Flash vs Step-3.5-Flash: Specs & Benchmark Comparison

CharacteristicGLM-4.7-FlashStep-3.5-Flash
CompanyZhipu AIStepFun
Release DateJanuary 18, 2026February 1, 2026
Parameters30B196B
MultimodalNoYes
Context (input)128K66K
Context (output)16K8K
Input Price / 1M$0.07$0.10
Output Price / 1M$0.40$0.40
Average Score0.60.8
Benchmarks
BrowseComp0.40.7
SWE-Bench Verified0.60.7
TAU-Bench0.80.9
AIME 20250.91.0

Visual Benchmark Comparison

GLM-4.7-Flash
Step-3.5-Flash
BrowseComp0.4 vs 0.7
0.4
0.7
SWE-Bench Verified0.6 vs 0.7
0.6
0.7
TAU-Bench0.8 vs 0.9
0.8
0.9
AIME 20250.9 vs 1.0
0.9
1.0

Verdict

GLM-4.7-Flash leads in 2 out of 5 comparison categories.

Overall Performance

Both models show comparable average scores: GLM-4.7-Flash — 0.6, Step-3.5-Flash — 0.8.

Programming

On SWE-Bench, both models are nearly equal: GLM-4.7-Flash — 0.6, Step-3.5-Flash — 0.7.

API Cost

GLM-4.7-Flash is 1.1x cheaper: input $0.07/1M vs $0.10/1M tokens.

Context Window

GLM-4.7-Flash supports a larger context: 128K vs 66K tokens.

Recency

Step-3.5-Flash is newer: released 2/1/2026 vs 1/18/2026.

More About These Models

Related Comparisons

The GLM-4.7-Flash and Step-3.5-Flash comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the GLM-4.7-Flash or Step-3.5-Flash page. See also the complete list of AI model comparisons.