Model Comparison

Kimi K2.5 vs Mercury 2

Kimi K2.5 significantly outperforms across most benchmarks. Mercury 2 is 2.9x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

Kimi K2.5 outperforms in 3 benchmarks (AIME 2025, GPQA, SciCode), while Mercury 2 is better at 0 benchmarks.

Kimi K2.5 significantly outperforms across most benchmarks.

Sun Apr 12 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Mercury 2 costs less

For input processing, Kimi K2.5 ($0.60/1M tokens) is 2.4x more expensive than Mercury 2 ($0.25/1M tokens).

For output processing, Kimi K2.5 ($2.50/1M tokens) is 3.3x more expensive than Mercury 2 ($0.75/1M tokens).

In conclusion, Kimi K2.5 is more expensive than Mercury 2.*

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

Lowest available price from all providers
Sun Apr 12 2026 • llm-stats.com
Moonshot AI
Kimi K2.5
Input tokens$0.60
Output tokens$2.50
Best providerFireworks
Inception
Mercury 2
Input tokens$0.25
Output tokens$0.75
Best providerInception
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Kimi K2.5 accepts 262,100 input tokens compared to Mercury 2's 128,000 tokens. Kimi K2.5 can generate longer responses up to 262,100 tokens, while Mercury 2 is limited to 8,192 tokens.

Moonshot AI
Kimi K2.5
Input262,100 tokens
Output262,100 tokens
Inception
Mercury 2
Input128,000 tokens
Output8,192 tokens
Sun Apr 12 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Kimi K2.5 supports multimodal inputs, whereas Mercury 2 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

Mercury 2

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi K2.5 is licensed under MIT, while Mercury 2 uses a proprietary license.

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

Kimi K2.5

MIT

Open weights

Mercury 2

Proprietary

Closed source

Release Timeline

When each model was launched

Kimi K2.5 was released on 2026-01-27, while Mercury 2 was released on 2026-02-24.

Mercury 2 is 1 month newer than Kimi K2.5.

Kimi K2.5

Jan 27, 2026

2 months ago

Mercury 2

Feb 24, 2026

1 months ago

4w 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 K2.5 is available from Fireworks. Mercury 2 is available from Inception.

Kimi K2.5

fireworks logo
Fireworks
Input Price:Input: $0.60/1MOutput Price:Output: $2.50/1M

Mercury 2

inception logo
Inception
Input Price:Input: $0.25/1MOutput Price:Output: $0.75/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Moonshot AI
Larger context window (262,100 tokens)
Supports multimodal inputs
Has open weights
Higher AIME 2025 score (96.1% vs 91.1%)
Higher GPQA score (87.6% vs 74.0%)
Higher SciCode score (48.7% vs 38.0%)
Inception
Less expensive input tokens
Less expensive output tokens

Detailed Comparison

AI Model Comparison Table
Feature
Moonshot AI
Kimi K2.5
Inception
Mercury 2

FAQ

Common questions about Kimi K2.5 vs Mercury 2

Kimi K2.5 significantly outperforms across most benchmarks. Kimi K2.5 is made by Moonshot AI and Mercury 2 is made by Inception. 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%. Mercury 2 scores AIME 2025: 91.1%, GPQA: 74.0%, IFBench: 71.0%, LiveCodeBench: 67.0%, Tau2 Airline: 53.0%.
Mercury 2 is 2.4x cheaper for input tokens. Kimi K2.5 costs $0.60/M input and $2.50/M output via fireworks. Mercury 2 costs $0.25/M input and $0.75/M output via inception.
Kimi K2.5 supports 262K tokens and Mercury 2 supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (262K vs 128K), input pricing ($0.60 vs $0.25/M), multimodal support (yes vs no), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.
Kimi K2.5 is developed by Moonshot AI and Mercury 2 is developed by Inception.