K-EXAONE-236B-A23B vs Step-3.5-Flash: Specs & Benchmark Comparison
| Characteristic | K-EXAONE-236B-A23B | Step-3.5-Flash |
|---|---|---|
| Company | LG AI Research | StepFun |
| Release Date | December 30, 2025 | February 1, 2026 |
| Parameters | 236B | 196B |
| Multimodal | No | Yes |
| Context (input) | 33K | 66K |
| Context (output) | 33K | 8K |
| Input Price / 1M | $0.60 | $0.10 |
| Output Price / 1M | $1.00 | $0.40 |
| Average Score | 0.8 | 0.8 |
| Benchmarks | ||
| LiveCodeBench v6 | 0.8 | 0.9 |
| AIME 2025 | 0.9 | 1.0 |
Visual Benchmark Comparison
K-EXAONE-236B-A23B
Step-3.5-Flash
LiveCodeBench v60.8 vs 0.9
0.8
0.9
AIME 20250.9 vs 1.0
0.9
1.0
Verdict
Step-3.5-Flash leads in 3 out of 4 comparison categories.
Overall Performance
Both models show comparable average scores: K-EXAONE-236B-A23B — 0.8, Step-3.5-Flash — 0.8.
API Cost
Step-3.5-Flash is 3.2x cheaper: input $0.10/1M vs $0.60/1M tokens.
Context Window
Step-3.5-Flash supports a larger context: 66K vs 33K tokens.
Recency
Step-3.5-Flash is newer: released 2/1/2026 vs 12/30/2025.
More About These Models
Related Comparisons
The K-EXAONE-236B-A23B 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 K-EXAONE-236B-A23B or Step-3.5-Flash page. See also the complete list of AI model comparisons.