The AI arena is free today

Open Superagent

Inkling-Small vs Kimi K3

Kimi K3 leads the LLM Stats Score 54.7 to 39.3. Inkling-Small is 11.4x cheaper per token.

Thinking Machines Lab · Moonshot AI · Updated for 2026

Which is better?

Kimi K3 leads the overall LLM Stats Score 54.7 to 39.3, ranking #5 overall.

In the 9 individual benchmarks reported for both models, Kimi K3 wins 9; this is a narrower head-to-head signal than the composite indexes.

On price, Inkling-Small is roughly 11.4x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Kimi K3 also accepts a larger context window (1,048,576 input tokens), making it the stronger choice for long documents and large codebases.

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

Choose Inkling-Small

  • cost matters — it's about 11.4x cheaper per token
  • you want the most recent training data — it shipped Jul 2026

Choose Kimi K3

  • overall performance matters — it scores 54.7 and ranks #5 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 9 of 9 exact shared results
  • you process long inputs — it offers a 1,048,576 token context window

At a glance

The differences that matter most.

Core performance indexes
39.3
#53
54.7
#5
39.0
#52
53.6
#4
31.1
#45
45.8
#5
24.8
#45
41.3
#4
Cost, coverage & limits
Benchmark wins
0 of 9
9 of 9
Input price
$0.30 / M
$3.00 / M
Output price
$1.20 / M
$15.00 / M
Context window
256,000
1,048,576

Capability indexes

Additional strengths measured across groups of related public benchmarks

4 shared
Index
Inkling-Small
Kimi K3
34.2#46
41.5#9
19.6#64
38.5#4
23.3#38
36.9#1
17.8#68
39.5#2
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

24 reported for Inkling-Small · 31 for Kimi K3

9 shared

Inkling-Small outperforms in 0 benchmarks, while Kimi K3 is better at 9 benchmarks (AA-Briefcase, BrowseComp, CharXiv-R, GPQA, Humanity's Last Exam, MCP Atlas, MMMU-Pro, Terminal-Bench 2.1, Toolathlon).

Kimi K3 significantly outperforms across most benchmarks.

Fri Aug 28 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Inkling-Small costs less

For input processing, Inkling-Small ($0.30/1M tokens) is 10.0x cheaper than Kimi K3 ($3.00/1M tokens).

For output processing, Inkling-Small ($1.20/1M tokens) is 12.5x cheaper than Kimi K3 ($15.00/1M tokens).

In conclusion, Kimi K3 is more expensive than Inkling-Small.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Fri Aug 28 2026 • llm-stats.com
Thinking Machines Lab
Inkling-Small
Input tokens$0.30
Output tokens$1.20
Best providerUnknown Organization
Moonshot AI
Kimi K3
Input tokens$3.00
Output tokens$15.00
Best providerFireworks
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

2524.0B diff

Kimi K3 has 2524.0B more parameters than Inkling-Small, making it 914.5% larger.

Thinking Machines Lab
Inkling-Small
276.0Bparameters
Moonshot AI
Kimi K3
2.8Tparameters
276.0B
Inkling-Small
2800.0B
Kimi K3

Context Window

Maximum input and output token capacity

Kimi K3 accepts 1,048,576 input tokens compared to Inkling-Small's 256,000 tokens. Kimi K3 can generate longer responses up to 1,048,576 tokens, while Inkling-Small is limited to 256,000 tokens.

Thinking Machines Lab
Inkling-Small
Input256,000 tokens
Output256,000 tokens
Moonshot AI
Kimi K3
Input1,048,576 tokens
Output1,048,576 tokens
Fri Aug 28 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Inkling-Small and Kimi K3 support multimodal inputs.

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

Inkling-Small

Text
Images
Audio
Video

Kimi K3

Text
Images
Audio
Video

License

Usage and distribution terms

Inkling-Small is licensed under Apache 2.0, while Kimi K3 uses Kimi K3 License.

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

Inkling-Small

Apache 2.0

Open weights

Kimi K3

Kimi K3 License

Open weights

Release Timeline

When each model was launched

Inkling-Small was released on 2026-07-30, while Kimi K3 was released on 2026-07-16.

Inkling-Small is 0 month newer than Kimi K3.

Inkling-Small

Jul 30, 2026

4 weeks ago

2w newer
Kimi K3

Jul 16, 2026

1 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

Provider Availability

Inkling-Small is available from Thinking Machines Lab. Kimi K3 is available from Fireworks, Moonshot AI, Novita, Together.

Inkling-Small

thinking-machines logo
Unknown Organization
Input Price:Input: $0.30/1MOutput Price:Output: $1.20/1M

Kimi K3

fireworks logo
Fireworks
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
moonshot logo
Unknown Organization
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
novita logo
Novita
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
together logo
Together
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Inkling-Small and Kimi K3 side-by-side, then vote on the output you prefer.

Inkling-Small
✓ Preferred
Kimi K3
Open in Playground

FAQ

Common questions about Inkling-Small vs Kimi K3.

Which is better, Inkling-Small or Kimi K3?

Kimi K3 leads the LLM Stats Score 54.7 to 39.3. Inkling-Small is made by Thinking Machines Lab and Kimi K3 is made by Moonshot AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Inkling-Small compare to Kimi K3 in benchmarks?

Inkling-Small scores AIME 2026: 95.5%, VoiceBench Avg: 90.1%, GPQA: 89.5%, Global-MMLU-Lite: 86.7%, ARC-AGI: 84.0%. Kimi K3 scores MathVision: 97.8%, DeepSearchQA: 95.0%, GPQA: 93.5%, CharXiv-R: 91.3%, BrowseComp: 91.2%.

Is Inkling-Small cheaper than Kimi K3?

Inkling-Small is 10.0x cheaper for input tokens. Inkling-Small costs $0.30/M input and $1.20/M output via thinking-machines. Kimi K3 costs $3.00/M input and $15.00/M output via fireworks.

What are the context window sizes for Inkling-Small and Kimi K3?

Inkling-Small supports 256K tokens and Kimi K3 supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Inkling-Small and Kimi K3?

Key differences include LLM Stats Score (39.3 vs 54.7), context window (256K vs 1.0M), input pricing ($0.30 vs $3.00/M), licensing (Apache 2.0 vs Kimi K3 License). See the full comparison above for benchmark-by-benchmark results.

Who makes Inkling-Small and Kimi K3?

Inkling-Small is developed by Thinking Machines Lab and Kimi K3 is developed by Moonshot AI.