Model Comparison

o3-mini vs Kimi K2 0905Which is better in 2026?

o3-mini shows notably better performance in the majority of benchmarks. Kimi K2 0905 is 1.8x cheaper per token.

Verdict: o3-mini vs Kimi K2 0905 — which is better?

o3-mini (by OpenAI) and Kimi K2 0905 (by Moonshot AI) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

o3-mini outperforms in 3 benchmarks (AIME 2024, GPQA, MATH), while Kimi K2 0905 is better at 1 benchmark (MMLU). o3-mini shows notably better performance in the majority of benchmarks.

On price, Kimi K2 0905 is roughly 1.8x 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.

Choose o3-mini if…

  • you want the strongest raw capability — it leads on 3 of 4 shared benchmarks

Choose Kimi K2 0905 if…

  • cost matters — it's about 1.8x cheaper per token
  • you process long inputs — it offers a 262,144 token context window
  • you want the most recent training data — it shipped Sep 2025

Performance Benchmarks

Comparative analysis across standard metrics

4 benchmarks

o3-mini outperforms in 3 benchmarks (AIME 2024, GPQA, MATH), while Kimi K2 0905 is better at 1 benchmark (MMLU).

o3-mini shows notably better performance in the majority of benchmarks.

Wed Jul 15 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Kimi K2 0905 costs less

For input processing, o3-mini ($1.10/1M tokens) is 1.8x more expensive than Kimi K2 0905 ($0.60/1M tokens).

For output processing, o3-mini ($4.40/1M tokens) is 1.8x more expensive than Kimi K2 0905 ($2.50/1M tokens).

In conclusion, o3-mini is more expensive than Kimi K2 0905.*

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

Lowest available price from all providers
Wed Jul 15 2026 • llm-stats.com
OpenAI
o3-mini
Input tokens$1.10
Output tokens$4.40
Best providerAzure
Moonshot AI
Kimi K2 0905
Input tokens$0.60
Output tokens$2.50
Best providerNovita
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Kimi K2 0905 accepts 262,144 input tokens compared to o3-mini's 200,000 tokens. Kimi K2 0905 can generate longer responses up to 262,144 tokens, while o3-mini is limited to 100,000 tokens.

OpenAI
o3-mini
Input200,000 tokens
Output100,000 tokens
Moonshot AI
Kimi K2 0905
Input262,144 tokens
Output262,144 tokens
Wed Jul 15 2026 • llm-stats.com

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

o3-mini

Proprietary

Closed source

Kimi K2 0905

Proprietary

Closed source

Release Timeline

When each model was launched

o3-mini was released on 2025-01-30, while Kimi K2 0905 was released on 2025-09-05.

Kimi K2 0905 is 7 months newer than o3-mini.

o3-mini

Jan 30, 2025

1.5 years ago

Kimi K2 0905

Sep 5, 2025

10 months ago

7mo newer

Knowledge Cutoff

When training data ends

o3-mini has a documented knowledge cutoff of 2023-09-30, while Kimi K2 0905's cutoff date is not specified.

We can confirm o3-mini's training data extends to 2023-09-30, but cannot make a direct comparison without Kimi K2 0905's cutoff date.

o3-mini

Sep 2023

Kimi K2 0905

—

Provider Availability

o3-mini is available from Azure, OpenAI. Kimi K2 0905 is available from Novita.

o3-mini

azure logo
Azure
Input Price:Input: $1.10/1MOutput Price:Output: $4.40/1M
openai logo
OpenAI
Input Price:Input: $1.10/1MOutput Price:Output: $4.40/1M

Kimi K2 0905

novita logo
Novita
Input Price:Input: $0.60/1MOutput Price:Output: $2.50/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

OpenAI
Higher AIME 2024 score (87.3% vs 72.0%)
Higher GPQA score (77.2% vs 75.8%)
Higher MATH score (97.9% vs 89.1%)
Moonshot AI
Larger context window (262,144 tokens)
Less expensive input tokens
Less expensive output tokens
Higher MMLU score (90.2% vs 86.9%)

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against o3-mini and Kimi K2 0905 side-by-side, then vote on the output you prefer.

o3-mini
✓ Preferred
Kimi K2 0905
Open in Playground
AI Model Comparison Table
Feature
OpenAI
o3-mini
Moonshot AI
Kimi K2 0905

FAQ

Common questions about o3-mini vs Kimi K2 0905.

Which is better, o3-mini or Kimi K2 0905?

o3-mini shows notably better performance in the majority of benchmarks. o3-mini is made by OpenAI and Kimi K2 0905 is made by Moonshot AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does o3-mini compare to Kimi K2 0905 in benchmarks?

o3-mini scores COLLIE: 98.7%, MATH: 97.9%, IFEval: 93.9%, MGSM: 92.0%, AIME 2024: 87.3%. Kimi K2 0905 scores HumanEval: 94.5%, MMLU: 90.2%, MATH: 89.1%, MMLU-Pro: 82.5%, GPQA: 75.8%.

Is o3-mini cheaper than Kimi K2 0905?

Kimi K2 0905 is 1.8x cheaper for input tokens. o3-mini costs $1.10/M input and $4.40/M output via azure. Kimi K2 0905 costs $0.60/M input and $2.50/M output via novita.

What are the context window sizes for o3-mini and Kimi K2 0905?

o3-mini supports 200K tokens and Kimi K2 0905 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 o3-mini and Kimi K2 0905?

Key differences include context window (200K vs 262K), input pricing ($1.10 vs $0.60/M). See the full comparison above for benchmark-by-benchmark results.

Who makes o3-mini and Kimi K2 0905?

o3-mini is developed by OpenAI and Kimi K2 0905 is developed by Moonshot AI.

Related comparisons