The AI arena is free today

Open Superagent

Kimi K2 Base vs Mercury 3

Mercury 3 leads the LLM Stats Score 36.1 to 13.0.

Moonshot AI · Inception · Updated for 2026

Which is better?

Mercury 3 leads the overall LLM Stats Score 36.1 to 13.0, ranking #98 overall.

In the 1 individual benchmarks reported for both models, Mercury 3 wins 1; this is a narrower head-to-head signal than the composite indexes.

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

Choose Kimi K2 Base

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

Choose Mercury 3

  • overall performance matters — it scores 36.1 and ranks #98 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • you want the most recent training data — it shipped Oct 2026

At a glance

The differences that matter most.

Kimi K2 Base
Moonshot AI
Mercury 3
Inception
Core performance indexes
LLM Stats Score
13.0
#270
36.1
#98
Reasoning
12.1
#268
34.8
#103
Coding
10.5
#185
21.5
#105
Cost, coverage & limits
Benchmark wins
0 of 1
1 of 1
Input price
— / M
$0.10 / M
Output price
— / M
$0.35 / M
Context window
—
1,000,000

Individual benchmarks

13 reported for Kimi K2 Base · 12 for Mercury 3

1 shared

Kimi K2 Base outperforms in 0 benchmarks, while Mercury 3 is better at 1 benchmark (GPQA).

Mercury 3 significantly outperforms across most benchmarks.

Thu Oct 22 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Mercury 3 specifies input context (1,000,000 tokens). Only Mercury 3 specifies output context (131,072 tokens).

Moonshot AI
Kimi K2 Base
Input- tokens
Output- tokens
Inception
Mercury 3
Input1,000,000 tokens
Output131,072 tokens
Thu Oct 22 2026 • llm-stats.com

License

Usage and distribution terms

Kimi K2 Base is licensed under MIT, while Mercury 3 uses a proprietary license.

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

Kimi K2 Base

MIT

Open weights

Mercury 3

Proprietary

Closed source

Release Timeline

When each model was launched

Kimi K2 Base was released on 2025-07-11, while Mercury 3 was released on 2026-10-19.

Mercury 3 is 16 months newer than Kimi K2 Base.

Kimi K2 Base

Jul 11, 2025

1.3 years ago

Mercury 3

Oct 19, 2026

3 days ago

1.3yr 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

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Kimi K2 Base and Mercury 3 side-by-side, then vote on the output you prefer.

Kimi K2 Base
✓ Preferred
Mercury 3
Open in Playground

FAQ

Common questions about Kimi K2 Base vs Mercury 3.

Which is better, Kimi K2 Base or Mercury 3?

Mercury 3 leads the LLM Stats Score 36.1 to 13.0. Kimi K2 Base is made by Moonshot AI and Mercury 3 is made by Inception. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Kimi K2 Base compare to Mercury 3 in benchmarks?

Kimi K2 Base scores C-Eval: 92.5%, GSM8k: 92.1%, MMLU-redux-2.0: 90.2%, MMLU: 87.8%, TriviaQA: 85.1%. Mercury 3 scores GPQA: 89.2%, AA-LCR: 77.7%, IFBench: 76.8%, MRCR v2: 75.5%, DeepSearchQA: 71.3%.

What are the context window sizes for Kimi K2 Base and Mercury 3?

Kimi K2 Base supports an unknown number of tokens and Mercury 3 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 Kimi K2 Base and Mercury 3?

Key differences include LLM Stats Score (13.0 vs 36.1), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Kimi K2 Base and Mercury 3?

Kimi K2 Base is developed by Moonshot AI and Mercury 3 is developed by Inception.

Related comparisons