The AI arena is free today

Open Superagent

Inkling 2 Mini vs Phi-3.5-vision-instruct

Inkling 2 Mini leads the LLM Stats Score 39.4 to -3.8.

Thinking Machines Lab · Microsoft · Updated for 2026

Which is better?

Inkling 2 Mini leads the overall LLM Stats Score 39.4 to -3.8, ranking #92 overall.

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

Choose Inkling 2 Mini

  • overall performance matters — it scores 39.4 and ranks #92 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Nov 2026

Choose Phi-3.5-vision-instruct

  • you are already invested in the Microsoft ecosystem

At a glance

The differences that matter most.

Core performance indexes
39.4
#92
-3.8
#400
38.7
#90
-5.4
#398
Cost, coverage & limits
Benchmark wins
—
—
Input price
$0.15 / M
— / M
Output price
$0.50 / M
— / M
Context window
1,000,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Inkling 2 Mini
Phi-3.5-vision-instruct
23.7#81
-3.8#234
24.1#76
-1.4#190
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

29 reported for Inkling 2 Mini · 9 for Phi-3.5-vision-instruct

No common benchmarks found

Inkling 2 Mini and Phi-3.5-vision-instructdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

22.2B diff

Inkling 2 Mini has 22.2B more parameters than Phi-3.5-vision-instruct, making it 528.6% larger.

Thinking Machines Lab
Inkling 2 Mini
26.4Bparameters
Microsoft
Phi-3.5-vision-instruct
4.2Bparameters
26.4B
Inkling 2 Mini
4.2B
Phi-3.5-vision-instruct

Context Window

Maximum input and output token capacity

Only Inkling 2 Mini specifies input context (1,000,000 tokens).

Thinking Machines Lab
Inkling 2 Mini
Input1,000,000 tokens
Output- tokens
Microsoft
Phi-3.5-vision-instruct
Input- tokens
Output- tokens
Sat Nov 21 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Inkling 2 Mini and Phi-3.5-vision-instruct support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Inkling 2 Mini

Text
Images
Audio
Video

Phi-3.5-vision-instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Inkling 2 Mini is licensed under Apache 2.0, while Phi-3.5-vision-instruct uses MIT.

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

Inkling 2 Mini

Apache 2.0

Open weights

Phi-3.5-vision-instruct

MIT

Open weights

Release Timeline

When each model was launched

Inkling 2 Mini was released on 2026-11-20, while Phi-3.5-vision-instruct was released on 2024-08-23.

Inkling 2 Mini is 27 months newer than Phi-3.5-vision-instruct.

Inkling 2 Mini

Nov 20, 2026

0 days ago

2.2yr newer
Phi-3.5-vision-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 Inkling 2 Mini and Phi-3.5-vision-instruct side-by-side, then vote on the output you prefer.

Inkling 2 Mini
✓ Preferred
Phi-3.5-vision-instruct
Open in Playground

FAQ

Common questions about Inkling 2 Mini vs Phi-3.5-vision-instruct.

Which is better, Inkling 2 Mini or Phi-3.5-vision-instruct?

Inkling 2 Mini leads the LLM Stats Score 39.4 to -3.8. Inkling 2 Mini is made by Thinking Machines Lab and Phi-3.5-vision-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 Inkling 2 Mini compare to Phi-3.5-vision-instruct in benchmarks?

Inkling 2 Mini scores OmniDocBench: 92.8%, DeepSearchQA: 85.3%, ARC-AGI: 84.5%, MCP Atlas: 82.7%, SWE-Bench Verified: 79.2%. Phi-3.5-vision-instruct scores ScienceQA: 91.3%, POPE: 86.1%, MMBench: 81.9%, ChartQA: 81.8%, AI2D: 78.1%.

What are the context window sizes for Inkling 2 Mini and Phi-3.5-vision-instruct?

Inkling 2 Mini supports 1.0M tokens and Phi-3.5-vision-instruct supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Inkling 2 Mini and Phi-3.5-vision-instruct?

Key differences include LLM Stats Score (39.4 vs -3.8), licensing (Apache 2.0 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Inkling 2 Mini and Phi-3.5-vision-instruct?

Inkling 2 Mini is developed by Thinking Machines Lab and Phi-3.5-vision-instruct is developed by Microsoft.