The AI arena is free today

Open Superagent

K2 Horizon 0.9B vs Phi-3.5-mini-instruct

K2 Horizon 0.9B leads the LLM Stats Score 0.5 to -4.3.

Institute of Foundation Models · Microsoft · Updated for 2026

Which is better?

K2 Horizon 0.9B leads the overall LLM Stats Score 0.5 to -4.3, ranking #358 overall.

In the 1 individual benchmarks reported for both models, Phi-3.5-mini-instruct 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 0.9B

  • overall performance matters — it scores 0.5 and ranks #358 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Sep 2026

Choose Phi-3.5-mini-instruct

  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results

At a glance

The differences that matter most.

K2 Horizon 0.9B
Institute of Foundation Models
Phi-3.5-mini-instruct
Microsoft
Core performance indexes
LLM Stats Score
0.5
#358
-4.3
#383
Reasoning
0.6
#350
-5.2
#379
Cost, coverage & limits
Benchmark wins
0 of 1
1 of 1
Input price
— / M
$0.10 / M
Output price
— / M
$0.10 / M
Context window
—
128,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
K2 Horizon 0.9B
Phi-3.5-mini-instruct
Math
3.3#308
-1.6#326
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

8 reported for K2 Horizon 0.9B · 31 for Phi-3.5-mini-instruct

1 shared

K2 Horizon 0.9B outperforms in 0 benchmarks, while Phi-3.5-mini-instruct is better at 1 benchmark (GPQA).

Phi-3.5-mini-instruct 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

2.9B diff

Phi-3.5-mini-instruct has 2.9B more parameters than K2 Horizon 0.9B, making it 322.2% larger.

Institute of Foundation Models
K2 Horizon 0.9B
900,000,000parameters
Microsoft
Phi-3.5-mini-instruct
3.8Bparameters
0.9B
K2 Horizon 0.9B
3.8B
Phi-3.5-mini-instruct

Context Window

Maximum input and output token capacity

Only Phi-3.5-mini-instruct specifies input context (128,000 tokens). Only Phi-3.5-mini-instruct specifies output context (128,000 tokens).

Institute of Foundation Models
K2 Horizon 0.9B
Input- tokens
Output- tokens
Microsoft
Phi-3.5-mini-instruct
Input128,000 tokens
Output128,000 tokens
Fri Oct 30 2026 • llm-stats.com

License

Usage and distribution terms

K2 Horizon 0.9B is licensed under Apache 2.0, while Phi-3.5-mini-instruct uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

K2 Horizon 0.9B

Apache 2.0

Open weights

Phi-3.5-mini-instruct

MIT

Open weights

Release Timeline

When each model was launched

K2 Horizon 0.9B was released on 2026-09-03, while Phi-3.5-mini-instruct was released on 2024-08-23.

K2 Horizon 0.9B is 25 months newer than Phi-3.5-mini-instruct.

K2 Horizon 0.9B

Sep 3, 2026

1 months ago

2.0yr newer
Phi-3.5-mini-instruct

Aug 23, 2024

2.2 years 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 0.9B and Phi-3.5-mini-instruct side-by-side, then vote on the output you prefer.

K2 Horizon 0.9B
✓ Preferred
Phi-3.5-mini-instruct
Open in Playground

FAQ

Common questions about K2 Horizon 0.9B vs Phi-3.5-mini-instruct.

Which is better, K2 Horizon 0.9B or Phi-3.5-mini-instruct?

K2 Horizon 0.9B leads the LLM Stats Score 0.5 to -4.3. K2 Horizon 0.9B is made by Institute of Foundation Models and Phi-3.5-mini-instruct is made by Microsoft. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does K2 Horizon 0.9B compare to Phi-3.5-mini-instruct in benchmarks?

K2 Horizon 0.9B scores HumanEval+: 79.9%, MBPP+: 68.0%, AIME 2026: 48.5%, AIME 2025: 41.7%, LiveCodeBench v6: 37.4%. Phi-3.5-mini-instruct scores GSM8k: 86.2%, ARC-C: 84.6%, RULER: 84.1%, PIQA: 81.0%, OpenBookQA: 79.2%.

What are the context window sizes for K2 Horizon 0.9B and Phi-3.5-mini-instruct?

K2 Horizon 0.9B supports an unknown number of tokens and Phi-3.5-mini-instruct supports 128K 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 0.9B and Phi-3.5-mini-instruct?

Key differences include LLM Stats Score (0.5 vs -4.3), licensing (Apache 2.0 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes K2 Horizon 0.9B and Phi-3.5-mini-instruct?

K2 Horizon 0.9B is developed by Institute of Foundation Models and Phi-3.5-mini-instruct is developed by Microsoft.

Related comparisons