Model Comparison

Kimi K2.5 vs Nemotron 3 Super (120B A12B)

Kimi K2.5 significantly outperforms across most benchmarks. Nemotron 3 Super (120B A12B) is 6.0x cheaper per token.

Performance Benchmarks

Comparative analysis across standard metrics

11 benchmarks

Kimi K2.5 outperforms in 11 benchmarks (AA-LCR, AIME 2025, BrowseComp, GPQA, HMMT 2025, Humanity's Last Exam, MMLU-Pro, SciCode, SWE-bench Multilingual, SWE-Bench Verified, Terminal-Bench 2.0), while Nemotron 3 Super (120B A12B) is better at 0 benchmarks.

Kimi K2.5 significantly outperforms across most benchmarks.

Sat Apr 18 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Nemotron 3 Super (120B A12B) costs less

For input processing, Kimi K2.5 ($0.60/1M tokens) is 6.0x more expensive than Nemotron 3 Super (120B A12B) ($0.10/1M tokens).

For output processing, Kimi K2.5 ($3.00/1M tokens) is 6.0x more expensive than Nemotron 3 Super (120B A12B) ($0.50/1M tokens).

In conclusion, Kimi K2.5 is more expensive than Nemotron 3 Super (120B A12B).*

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

Lowest available price from all providers
Sat Apr 18 2026 • llm-stats.com
Moonshot AI
Kimi K2.5
Input tokens$0.60
Output tokens$3.00
Best providerFireworks
NVIDIA
Nemotron 3 Super (120B A12B)
Input tokens$0.10
Output tokens$0.50
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

880.0B diff

Kimi K2.5 has 880.0B more parameters than Nemotron 3 Super (120B A12B), making it 733.3% larger.

Moonshot AI
Kimi K2.5
1000.0Bparameters
NVIDIA
Nemotron 3 Super (120B A12B)
120.0Bparameters
1000.0B
Kimi K2.5
120.0B
Nemotron 3 Super (120B A12B)

Context Window

Maximum input and output token capacity

Nemotron 3 Super (120B A12B) accepts 262,144 input tokens compared to Kimi K2.5's 262,100 tokens. Nemotron 3 Super (120B A12B) can generate longer responses up to 262,144 tokens, while Kimi K2.5 is limited to 262,100 tokens.

Moonshot AI
Kimi K2.5
Input262,100 tokens
Output262,100 tokens
NVIDIA
Nemotron 3 Super (120B A12B)
Input262,144 tokens
Output262,144 tokens
Sat Apr 18 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Kimi K2.5 supports multimodal inputs, whereas Nemotron 3 Super (120B A12B) does not.

Kimi K2.5 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Kimi K2.5

Text
Images
Audio
Video

Nemotron 3 Super (120B A12B)

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi K2.5 is licensed under MIT, while Nemotron 3 Super (120B A12B) uses NVIDIA Open Model License Agreement .

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

Kimi K2.5

MIT

Open weights

Nemotron 3 Super (120B A12B)

NVIDIA Open Model License Agreement

Open weights

Release Timeline

When each model was launched

Kimi K2.5 was released on 2026-01-27, while Nemotron 3 Super (120B A12B) was released on 2026-03-11.

Nemotron 3 Super (120B A12B) is 1 month newer than Kimi K2.5.

Kimi K2.5

Jan 27, 2026

2 months ago

Nemotron 3 Super (120B A12B)

Mar 11, 2026

1 months ago

1mo newer

Knowledge Cutoff

When training data ends

Nemotron 3 Super (120B A12B) has a documented knowledge cutoff of 2025-06-01, while Kimi K2.5's cutoff date is not specified.

We can confirm Nemotron 3 Super (120B A12B)'s training data extends to 2025-06-01, but cannot make a direct comparison without Kimi K2.5's cutoff date.

Kimi K2.5

Nemotron 3 Super (120B A12B)

Jun 2025

Provider Availability

Kimi K2.5 is available from Fireworks, Moonshot AI. Nemotron 3 Super (120B A12B) is available from DeepInfra.

Kimi K2.5

fireworks logo
Fireworks
Input Price:Input: $0.60/1MOutput Price:Output: $3.00/1M
moonshot logo
Unknown Organization
Input Price:Input: $0.60/1MOutput Price:Output: $3.00/1M

Nemotron 3 Super (120B A12B)

deepinfra logo
Deepinfra
Input Price:Input: $0.10/1MOutput Price:Output: $0.50/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Key Takeaways

Supports multimodal inputs
Higher AA-LCR score (70.0% vs 58.3%)
Higher AIME 2025 score (96.1% vs 90.2%)
Higher BrowseComp score (74.9% vs 31.3%)
Higher GPQA score (87.6% vs 82.7%)
Higher HMMT 2025 score (95.4% vs 94.7%)
Higher Humanity's Last Exam score (50.2% vs 22.8%)
Higher MMLU-Pro score (87.1% vs 83.7%)
Higher SciCode score (48.7% vs 42.0%)
Higher SWE-bench Multilingual score (73.0% vs 45.8%)
Higher SWE-Bench Verified score (76.8% vs 53.7%)
Higher Terminal-Bench 2.0 score (50.8% vs 31.0%)
Larger context window (262,144 tokens)
Less expensive input tokens
Less expensive output tokens

Detailed Comparison

AI Model Comparison Table
Feature
Moonshot AI
Kimi K2.5
NVIDIA
Nemotron 3 Super (120B A12B)

FAQ

Common questions about Kimi K2.5 vs Nemotron 3 Super (120B A12B)

Kimi K2.5 significantly outperforms across most benchmarks. Kimi K2.5 is made by Moonshot AI and Nemotron 3 Super (120B A12B) is made by NVIDIA. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
Kimi K2.5 scores AIME 2025: 96.1%, HMMT 2025: 95.4%, InfoVQAtest: 92.6%, OCRBench: 92.3%, MathVista-Mini: 90.1%. Nemotron 3 Super (120B A12B) scores HMMT 2025: 94.7%, RULER: 91.8%, AIME 2025: 90.2%, WMT24++: 86.7%, MMLU-Pro: 83.7%.
Nemotron 3 Super (120B A12B) is 6.0x cheaper for input tokens. Kimi K2.5 costs $0.60/M input and $3.00/M output via fireworks. Nemotron 3 Super (120B A12B) costs $0.10/M input and $0.50/M output via deepinfra.
Kimi K2.5 supports 262K tokens and Nemotron 3 Super (120B A12B) supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (262K vs 262K), input pricing ($0.60 vs $0.10/M), multimodal support (yes vs no), licensing (MIT vs NVIDIA Open Model License Agreement ). See the full comparison above for benchmark-by-benchmark results.
Kimi K2.5 is developed by Moonshot AI and Nemotron 3 Super (120B A12B) is developed by NVIDIA.