The AI arena is free today

Open Superagent

K2 Horizon 375B-A23B vs Step-3.5-Flash

K2 Horizon 375B-A23B and Step-3.5-Flash are closely matched at 38.5 and 36.5 on the LLM Stats Score.

Institute of Foundation Models · StepFun · Updated for 2026

Which is better?

K2 Horizon 375B-A23B and Step-3.5-Flash are closely matched on the overall LLM Stats Score at 38.5 and 36.5.

In the 1 individual benchmarks reported for both models, K2 Horizon 375B-A23B wins 1; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose K2 Horizon 375B-A23B

  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • you want the most recent training data — it shipped Sep 2026

Choose Step-3.5-Flash

  • you want predictable pricing at $0.10/M input and $0.40/M output

At a glance

The differences that matter most.

K2 Horizon 375B-A23B
Institute of Foundation Models
Step-3.5-Flash
StepFun
Core performance indexes
LLM Stats Score
38.5
#83
36.5
#94
Reasoning
37.3
#87
36.5
#94
Coding
21.2
#114
20.5
#120
Agents
23.9
#74
15.0
#115
Cost, coverage & limits
Benchmark wins
1 of 1
0 of 1
Input price
— / M
$0.10 / M
Output price
— / M
$0.40 / M
Context window
—
65,536

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
K2 Horizon 375B-A23B
Step-3.5-Flash
Math
29.7#89
34.0#55
Tool use
22.3#62
13.2#123
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

18 reported for K2 Horizon 375B-A23B · 7 for Step-3.5-Flash

1 shared

K2 Horizon 375B-A23B outperforms in 1 benchmarks (BrowseComp), while Step-3.5-Flash is better at 0 benchmarks.

K2 Horizon 375B-A23B significantly outperforms across most benchmarks.

Fri Oct 30 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

179.0B diff

K2 Horizon 375B-A23B has 179.0B more parameters than Step-3.5-Flash, making it 91.3% larger.

Institute of Foundation Models
K2 Horizon 375B-A23B
375.0Bparameters
StepFun
Step-3.5-Flash
196.0Bparameters
375.0B
K2 Horizon 375B-A23B
196.0B
Step-3.5-Flash

Context Window

Maximum input and output token capacity

Only Step-3.5-Flash specifies input context (65,536 tokens). Only Step-3.5-Flash specifies output context (8,192 tokens).

Institute of Foundation Models
K2 Horizon 375B-A23B
Input- tokens
Output- tokens
StepFun
Step-3.5-Flash
Input65,536 tokens
Output8,192 tokens
Fri Oct 30 2026 • llm-stats.com

License

Usage and distribution terms

Both models are licensed under Apache 2.0.

Both models share the same licensing terms, providing consistent usage rights.

K2 Horizon 375B-A23B

Apache 2.0

Open weights

Step-3.5-Flash

Apache 2.0

Open weights

Release Timeline

When each model was launched

K2 Horizon 375B-A23B was released on 2026-09-03, while Step-3.5-Flash was released on 2026-02-02.

K2 Horizon 375B-A23B is 7 months newer than Step-3.5-Flash.

K2 Horizon 375B-A23B

Sep 3, 2026

1 months ago

7mo newer
Step-3.5-Flash

Feb 2, 2026

9 months ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against K2 Horizon 375B-A23B and Step-3.5-Flash side-by-side, then vote on the output you prefer.

K2 Horizon 375B-A23B
✓ Preferred
Step-3.5-Flash
Open in Playground

FAQ

Common questions about K2 Horizon 375B-A23B vs Step-3.5-Flash.

Which is better, K2 Horizon 375B-A23B or Step-3.5-Flash?

K2 Horizon 375B-A23B and Step-3.5-Flash are closely matched on the LLM Stats Score at 38.5 and 36.5. K2 Horizon 375B-A23B is made by Institute of Foundation Models and Step-3.5-Flash is made by StepFun. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does K2 Horizon 375B-A23B compare to Step-3.5-Flash in benchmarks?

K2 Horizon 375B-A23B scores GPQA: 87.3%, AA-LCR: 76.0%, OmniScience (non-hallucination rate): 74.7%, BrowseComp: 72.8%, Terminal-Bench 2.1: 70.2%. Step-3.5-Flash scores AIME 2025: 97.3%, Tau-bench: 88.2%, LiveCodeBench v6: 86.4%, IMO-AnswerBench: 85.4%, SWE-Bench Verified: 74.4%.

What are the context window sizes for K2 Horizon 375B-A23B and Step-3.5-Flash?

K2 Horizon 375B-A23B supports an unknown number of tokens and Step-3.5-Flash supports 66K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between K2 Horizon 375B-A23B and Step-3.5-Flash?

Key differences include LLM Stats Score (38.5 vs 36.5). See the full comparison above for benchmark-by-benchmark results.

Who makes K2 Horizon 375B-A23B and Step-3.5-Flash?

K2 Horizon 375B-A23B is developed by Institute of Foundation Models and Step-3.5-Flash is developed by StepFun.

Related comparisons