The AI arena is free today

Open Superagent

Kimi-k1.5 vs Llama 3.1 405B Instruct

Kimi-k1.5 and Llama 3.1 405B Instruct are closely matched at 17.2 and 14.7 on the LLM Stats Score.

Moonshot AI · Meta · Updated for 2026

Which is better?

Kimi-k1.5 and Llama 3.1 405B Instruct are closely matched on the overall LLM Stats Score at 17.2 and 14.7.

The models split the 2 individual benchmarks reported for both models evenly.

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

Choose Kimi-k1.5

  • you want the most recent training data — it shipped Jan 2025

Choose Llama 3.1 405B Instruct

  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Core performance indexes
17.2
#218
14.7
#233
16.4
#215
13.8
#233
Cost, coverage & limits
Benchmark wins
1 of 2
1 of 2
Input price
— / M
$0.89 / M
Output price
— / M
$0.89 / M
Context window
128,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Kimi-k1.5
Llama 3.1 405B Instruct
20.2#160
19.3#168
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

9 reported for Kimi-k1.5 · 18 for Llama 3.1 405B Instruct

2 shared

Kimi-k1.5 outperforms in 1 benchmarks (MMLU), while Llama 3.1 405B Instruct is better at 1 benchmark (IFEval).

Both models are evenly matched across the benchmarks.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Llama 3.1 405B Instruct specifies input context (128,000 tokens). Only Llama 3.1 405B Instruct specifies output context (128,000 tokens).

Moonshot AI
Kimi-k1.5
Input- tokens
Output- tokens
Meta
Llama 3.1 405B Instruct
Input128,000 tokens
Output128,000 tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Kimi-k1.5 supports multimodal inputs, whereas Llama 3.1 405B Instruct does not.

Kimi-k1.5 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Kimi-k1.5

Text
Images
Audio
Video

Llama 3.1 405B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi-k1.5 is licensed under a proprietary license, while Llama 3.1 405B Instruct uses Llama 3.1 Community License.

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

Kimi-k1.5

Proprietary

Closed source

Llama 3.1 405B Instruct

Llama 3.1 Community License

Open weights

Release Timeline

When each model was launched

Kimi-k1.5 was released on 2025-01-20, while Llama 3.1 405B Instruct was released on 2024-07-23.

Kimi-k1.5 is 6 months newer than Llama 3.1 405B Instruct.

Kimi-k1.5

Jan 20, 2025

1.7 years ago

6mo newer
Llama 3.1 405B Instruct

Jul 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?Start an Issue discussion

Judge for yourself.

Run your own prompts against Kimi-k1.5 and Llama 3.1 405B Instruct side-by-side, then vote on the output you prefer.

Kimi-k1.5
✓ Preferred
Llama 3.1 405B Instruct
Open in Playground

FAQ

Common questions about Kimi-k1.5 vs Llama 3.1 405B Instruct.

Which is better, Kimi-k1.5 or Llama 3.1 405B Instruct?

Kimi-k1.5 and Llama 3.1 405B Instruct are closely matched on the LLM Stats Score at 17.2 and 14.7. Kimi-k1.5 is made by Moonshot AI and Llama 3.1 405B Instruct is made by Meta. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Kimi-k1.5 compare to Llama 3.1 405B Instruct in benchmarks?

Kimi-k1.5 scores MATH-500: 96.2%, CLUEWSC: 91.4%, C-Eval: 88.3%, MMLU: 87.4%, IFEval: 87.2%. Llama 3.1 405B Instruct scores ARC-C: 96.9%, GSM8k: 96.8%, API-Bank: 92.0%, Multilingual MGSM (CoT): 91.6%, HumanEval: 89.0%.

What are the context window sizes for Kimi-k1.5 and Llama 3.1 405B Instruct?

Kimi-k1.5 supports an unknown number of tokens and Llama 3.1 405B 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 Kimi-k1.5 and Llama 3.1 405B Instruct?

Key differences include LLM Stats Score (17.2 vs 14.7), multimodal support (yes vs no), licensing (Proprietary vs Llama 3.1 Community License). See the full comparison above for benchmark-by-benchmark results.

Who makes Kimi-k1.5 and Llama 3.1 405B Instruct?

Kimi-k1.5 is developed by Moonshot AI and Llama 3.1 405B Instruct is developed by Meta.