The AI arena is free today

Open Superagent

Kimi K2 0905 vs Mistral Small 3.1 24B Base

Kimi K2 0905 leads the LLM Stats Score 21.6 to 0.3. Mistral Small 3.1 24B Base is 7.2x cheaper per token.

Moonshot AI · Mistral AI · Updated for 2026

Which is better?

Kimi K2 0905 leads the overall LLM Stats Score 21.6 to 0.3, ranking #185 overall.

In the 3 individual benchmarks reported for both models, Kimi K2 0905 wins 3; this is a narrower head-to-head signal than the composite indexes.

On price, Mistral Small 3.1 24B Base is roughly 7.2x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Kimi K2 0905 also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.

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

Choose Kimi K2 0905

  • overall performance matters — it scores 21.6 and ranks #185 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 3 of 3 exact shared results
  • you process long inputs — it offers a 262,144 token context window
  • you want the most recent training data — it shipped Sep 2025

Choose Mistral Small 3.1 24B Base

  • cost matters — it's about 7.2x cheaper per token
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Kimi K2 0905
Moonshot AI
Mistral Small 3.1 24B Base
Mistral AI
Core performance indexes
LLM Stats Score
21.6
#185
0.3
#325
Reasoning
22.0
#173
0.5
#316
Cost, coverage & limits
Benchmark wins
3 of 3
0 of 3
Input price
$0.60 / M
$0.10 / M
Output price
$2.50 / M
$0.30 / M
Context window
262,144
128,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
Kimi K2 0905
Mistral Small 3.1 24B Base
Math
24.3#117
4.7#279
Finance
26.6#42
5.3#169
Legal
26.6#32
5.3#155
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

6 reported for Kimi K2 0905 · 5 for Mistral Small 3.1 24B Base

3 shared

Kimi K2 0905 outperforms in 3 benchmarks (GPQA, MMLU, MMLU-Pro), while Mistral Small 3.1 24B Base is better at 0 benchmarks.

Kimi K2 0905 significantly outperforms across most benchmarks.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Mistral Small 3.1 24B Base costs less

For input processing, Kimi K2 0905 ($0.60/1M tokens) is 6.0x more expensive than Mistral Small 3.1 24B Base ($0.10/1M tokens).

For output processing, Kimi K2 0905 ($2.50/1M tokens) is 8.3x more expensive than Mistral Small 3.1 24B Base ($0.30/1M tokens).

In conclusion, Kimi K2 0905 is more expensive than Mistral Small 3.1 24B Base.*

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

Lowest available price from all providers
Sun Sep 20 2026 • llm-stats.com
Moonshot AI
Kimi K2 0905
Input tokens$0.60
Output tokens$2.50
Best providerNovita
Mistral AI
Mistral Small 3.1 24B Base
Input tokens$0.10
Output tokens$0.30
Best providerMistral
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

976.0B diff

Kimi K2 0905 has 976.0B more parameters than Mistral Small 3.1 24B Base, making it 4066.7% larger.

Moonshot AI
Kimi K2 0905
1.0Tparameters
Mistral AI
Mistral Small 3.1 24B Base
24.0Bparameters
1000.0B
Kimi K2 0905
24.0B
Mistral Small 3.1 24B Base

Context Window

Maximum input and output token capacity

Kimi K2 0905 accepts 262,144 input tokens compared to Mistral Small 3.1 24B Base's 128,000 tokens. Kimi K2 0905 can generate longer responses up to 262,144 tokens, while Mistral Small 3.1 24B Base is limited to 128,000 tokens.

Moonshot AI
Kimi K2 0905
Input262,144 tokens
Output262,144 tokens
Mistral AI
Mistral Small 3.1 24B Base
Input128,000 tokens
Output128,000 tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Mistral Small 3.1 24B Base supports multimodal inputs, whereas Kimi K2 0905 does not.

Mistral Small 3.1 24B Base can handle both text and other forms of data like images, making it suitable for multimodal applications.

Kimi K2 0905

Text
Images
Audio
Video

Mistral Small 3.1 24B Base

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi K2 0905 is licensed under a proprietary license, while Mistral Small 3.1 24B Base uses Apache 2.0.

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

Kimi K2 0905

Proprietary

Closed source

Mistral Small 3.1 24B Base

Apache 2.0

Open weights

Release Timeline

When each model was launched

Kimi K2 0905 was released on 2025-09-05, while Mistral Small 3.1 24B Base was released on 2025-03-17.

Kimi K2 0905 is 6 months newer than Mistral Small 3.1 24B Base.

Kimi K2 0905

Sep 5, 2025

1.0 years ago

5mo newer
Mistral Small 3.1 24B Base

Mar 17, 2025

1.5 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

Provider Availability

Kimi K2 0905 is available from Novita. Mistral Small 3.1 24B Base is available from Mistral AI.

Kimi K2 0905

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

Mistral Small 3.1 24B Base

mistral logo
Mistral
Input Price:Input: $0.10/1MOutput Price:Output: $0.30/1M
* 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 Mistral Small 3.1 24B Base side-by-side, then vote on the output you prefer.

Kimi K2 0905
✓ Preferred
Mistral Small 3.1 24B Base
Open in Playground

FAQ

Common questions about Kimi K2 0905 vs Mistral Small 3.1 24B Base.

Which is better, Kimi K2 0905 or Mistral Small 3.1 24B Base?

Kimi K2 0905 leads the LLM Stats Score 21.6 to 0.3. Kimi K2 0905 is made by Moonshot AI and Mistral Small 3.1 24B Base is made by Mistral AI. 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 Mistral Small 3.1 24B Base in benchmarks?

Kimi K2 0905 scores HumanEval: 94.5%, MMLU: 90.2%, MATH: 89.1%, MMLU-Pro: 82.5%, GPQA: 75.8%. Mistral Small 3.1 24B Base scores MMLU: 81.0%, TriviaQA: 80.5%, MMMU: 59.3%, MMLU-Pro: 56.0%, GPQA: 37.5%.

Is Kimi K2 0905 cheaper than Mistral Small 3.1 24B Base?

Mistral Small 3.1 24B Base is 6.0x cheaper for input tokens. Kimi K2 0905 costs $0.60/M input and $2.50/M output via novita. Mistral Small 3.1 24B Base costs $0.10/M input and $0.30/M output via mistral.

What are the context window sizes for Kimi K2 0905 and Mistral Small 3.1 24B Base?

Kimi K2 0905 supports 262K tokens and Mistral Small 3.1 24B Base 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 K2 0905 and Mistral Small 3.1 24B Base?

Key differences include LLM Stats Score (21.6 vs 0.3), context window (262K vs 128K), input pricing ($0.60 vs $0.10/M), multimodal support (no vs yes), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Kimi K2 0905 and Mistral Small 3.1 24B Base?

Kimi K2 0905 is developed by Moonshot AI and Mistral Small 3.1 24B Base is developed by Mistral AI.

Related comparisons