The AI arena is free today

Open Superagent

Kimi K2 0905 vs Nemotron 3.5 Lightning (30B A3B)

Kimi K2 0905 and Nemotron 3.5 Lightning (30B A3B) are closely matched at 21.6 and 22.1 on the LLM Stats Score. Nemotron 3.5 Lightning (30B A3B) is 9.8x cheaper per token.

Moonshot AI · NVIDIA · Updated for 2026

Which is better?

Kimi K2 0905 and Nemotron 3.5 Lightning (30B A3B) are closely matched on the overall LLM Stats Score at 21.6 and 22.1.

In the 2 individual benchmarks reported for both models, Kimi K2 0905 wins 2; this is a narrower head-to-head signal than the composite indexes.

On price, Nemotron 3.5 Lightning (30B A3B) is roughly 9.8x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

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

Choose Kimi K2 0905

  • your work emphasizes coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 2 of 2 exact shared results

Choose Nemotron 3.5 Lightning (30B A3B)

  • cost matters — it's about 9.8x cheaper per token
  • you want the most recent training data — it shipped Aug 2026
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Kimi K2 0905
Moonshot AI
Nemotron 3.5 Lightning (30B A3B)
NVIDIA
Core performance indexes
LLM Stats Score
21.6
#188
22.1
#181
Reasoning
22.0
#176
19.6
#200
Coding
19.4
#107
8.4
#184
Cost, coverage & limits
Benchmark wins
2 of 2
0 of 2
Input price
$0.60 / M
$0.08 / M
Output price
$2.50 / M
$0.20 / M
Context window
262,144
262,144

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Kimi K2 0905
Nemotron 3.5 Lightning (30B A3B)
Math
24.3#117
17.9#189
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

6 reported for Kimi K2 0905 · 13 for Nemotron 3.5 Lightning (30B A3B)

2 shared

Kimi K2 0905 outperforms in 2 benchmarks (GPQA, MMLU-Pro), while Nemotron 3.5 Lightning (30B A3B) is better at 0 benchmarks.

Kimi K2 0905 significantly outperforms across most benchmarks.

Tue Sep 22 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Nemotron 3.5 Lightning (30B A3B) costs less

For input processing, Kimi K2 0905 ($0.60/1M tokens) is 7.5x more expensive than Nemotron 3.5 Lightning (30B A3B) ($0.08/1M tokens).

For output processing, Kimi K2 0905 ($2.50/1M tokens) is 12.5x more expensive than Nemotron 3.5 Lightning (30B A3B) ($0.20/1M tokens).

In conclusion, Kimi K2 0905 is more expensive than Nemotron 3.5 Lightning (30B A3B).*

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

Lowest available price from all providers
Tue Sep 22 2026 • llm-stats.com
Moonshot AI
Kimi K2 0905
Input tokens$0.60
Output tokens$2.50
Best providerNovita
NVIDIA
Nemotron 3.5 Lightning (30B A3B)
Input tokens$0.08
Output tokens$0.20
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

970.0B diff

Kimi K2 0905 has 970.0B more parameters than Nemotron 3.5 Lightning (30B A3B), making it 3233.3% larger.

Moonshot AI
Kimi K2 0905
1.0Tparameters
NVIDIA
Nemotron 3.5 Lightning (30B A3B)
30.0Bparameters
1000.0B
Kimi K2 0905
30.0B
Nemotron 3.5 Lightning (30B A3B)

Context Window

Maximum input and output token capacity

Both models have the same input context window of 262,144 tokens. Both models can generate responses up to 262,144 tokens.

Moonshot AI
Kimi K2 0905
Input262,144 tokens
Output262,144 tokens
NVIDIA
Nemotron 3.5 Lightning (30B A3B)
Input262,144 tokens
Output262,144 tokens
Tue Sep 22 2026 • llm-stats.com

License

Usage and distribution terms

Kimi K2 0905 is licensed under a proprietary license, while Nemotron 3.5 Lightning (30B A3B) uses OpenMDW License v1.1.

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

Kimi K2 0905

Proprietary

Closed source

Nemotron 3.5 Lightning (30B A3B)

OpenMDW License v1.1

Open weights

Release Timeline

When each model was launched

Kimi K2 0905 was released on 2025-09-05, while Nemotron 3.5 Lightning (30B A3B) was released on 2026-08-11.

Nemotron 3.5 Lightning (30B A3B) is 11 months newer than Kimi K2 0905.

Kimi K2 0905

Sep 5, 2025

1.0 years ago

Nemotron 3.5 Lightning (30B A3B)

Aug 11, 2026

1 months ago

11mo newer

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

Kimi K2 0905 is available from Novita. Nemotron 3.5 Lightning (30B A3B) is available from DeepInfra.

Kimi K2 0905

novita logo
Novita
Input Price:Input: $0.60/1MOutput Price:Output: $2.50/1M

Nemotron 3.5 Lightning (30B A3B)

deepinfra logo
Deepinfra
Input Price:Input: $0.08/1MOutput Price:Output: $0.20/1M
* 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 Kimi K2 0905 and Nemotron 3.5 Lightning (30B A3B) side-by-side, then vote on the output you prefer.

Kimi K2 0905
✓ Preferred
Nemotron 3.5 Lightning (30B A3B)
Open in Playground

FAQ

Common questions about Kimi K2 0905 vs Nemotron 3.5 Lightning (30B A3B).

Which is better, Kimi K2 0905 or Nemotron 3.5 Lightning (30B A3B)?

Kimi K2 0905 and Nemotron 3.5 Lightning (30B A3B) are closely matched on the LLM Stats Score at 21.6 and 22.1. Kimi K2 0905 is made by Moonshot AI and Nemotron 3.5 Lightning (30B A3B) is made by NVIDIA. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Kimi K2 0905 compare to Nemotron 3.5 Lightning (30B A3B) in benchmarks?

Kimi K2 0905 scores HumanEval: 94.5%, MMLU: 90.2%, MATH: 89.1%, MMLU-Pro: 82.5%, GPQA: 75.8%. Nemotron 3.5 Lightning (30B A3B) scores PinchBench: 85.4%, MMLU-Pro: 81.9%, GPQA: 75.4%, IFBench: 71.9%, AA-LCR: 52.0%.

Is Kimi K2 0905 cheaper than Nemotron 3.5 Lightning (30B A3B)?

Nemotron 3.5 Lightning (30B A3B) is 7.5x cheaper for input tokens. Kimi K2 0905 costs $0.60/M input and $2.50/M output via novita. Nemotron 3.5 Lightning (30B A3B) costs $0.08/M input and $0.20/M output via deepinfra.

What are the context window sizes for Kimi K2 0905 and Nemotron 3.5 Lightning (30B A3B)?

Kimi K2 0905 supports 262K tokens and Nemotron 3.5 Lightning (30B A3B) supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Kimi K2 0905 and Nemotron 3.5 Lightning (30B A3B)?

Key differences include LLM Stats Score (21.6 vs 22.1), input pricing ($0.60 vs $0.08/M), licensing (Proprietary vs OpenMDW License v1.1). See the full comparison above for benchmark-by-benchmark results.

Who makes Kimi K2 0905 and Nemotron 3.5 Lightning (30B A3B)?

Kimi K2 0905 is developed by Moonshot AI and Nemotron 3.5 Lightning (30B A3B) is developed by NVIDIA.

Related comparisons