Model Comparison

o1 vs Claude 3.5 HaikuWhich is better in 2026?

o1 significantly outperforms across most benchmarks. Claude 3.5 Haiku is 16.4x cheaper per token.

Verdict: o1 vs Claude 3.5 Haiku — which is better?

o1 (by OpenAI) and Claude 3.5 Haiku (by Anthropic) 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.

o1 outperforms in 6 benchmarks (GPQA, MATH, MGSM, SWE-Bench Verified, TAU-bench Airline, TAU-bench Retail), while Claude 3.5 Haiku is better at 0 benchmarks. o1 significantly outperforms across most benchmarks.

On price, Claude 3.5 Haiku is roughly 16.4x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Choose o1 if…

  • you want the strongest raw capability — it leads on 6 of 7 shared benchmarks
  • you want the most recent training data — it shipped Dec 2024

Choose Claude 3.5 Haiku if…

  • cost matters — it's about 16.4x cheaper per token
Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

7 benchmarks

o1 outperforms in 6 benchmarks (GPQA, MATH, MGSM, SWE-Bench Verified, TAU-bench Airline, TAU-bench Retail), while Claude 3.5 Haiku is better at 0 benchmarks.

o1 significantly outperforms across most benchmarks.

Sat Jun 13 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Claude 3.5 Haiku costs less

For input processing, o1 ($15.00/1M tokens) is 18.8x more expensive than Claude 3.5 Haiku ($0.80/1M tokens).

For output processing, o1 ($60.00/1M tokens) is 15.0x more expensive than Claude 3.5 Haiku ($4.00/1M tokens).

In conclusion, o1 is more expensive than Claude 3.5 Haiku.*

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

Lowest available price from all providers
Sat Jun 13 2026 • llm-stats.com
OpenAI
o1
Input tokens$15.00
Output tokens$60.00
Best providerAzure
Anthropic
Claude 3.5 Haiku
Input tokens$0.80
Output tokens$4.00
Best providerAWS Bedrock
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Both models have the same input context window of 200,000 tokens. Claude 3.5 Haiku can generate longer responses up to 200,000 tokens, while o1 is limited to 100,000 tokens.

OpenAI
o1
Input200,000 tokens
Output100,000 tokens
Anthropic
Claude 3.5 Haiku
Input200,000 tokens
Output200,000 tokens
Sat Jun 13 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.

o1

Proprietary

Closed source

Claude 3.5 Haiku

Proprietary

Closed source

Release Timeline

When each model was launched

o1 was released on 2024-12-17, while Claude 3.5 Haiku was released on 2024-10-22.

o1 is 2 months newer than Claude 3.5 Haiku.

o1

Dec 17, 2024

1.5 years ago

1mo newer
Claude 3.5 Haiku

Oct 22, 2024

1.6 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

o1 is available from Azure, OpenAI. Claude 3.5 Haiku is available from Bedrock, Google, Anthropic.

o1

azure logo
Azure
Input Price:Input: $15.00/1MOutput Price:Output: $60.00/1M
openai logo
OpenAI
Input Price:Input: $15.00/1MOutput Price:Output: $60.00/1M

Claude 3.5 Haiku

bedrock logo
AWS Bedrock
Input Price:Input: $0.80/1MOutput Price:Output: $4.00/1M
google logo
Google
Input Price:Input: $0.80/1MOutput Price:Output: $4.00/1M
anthropic logo
Anthropic
Input Price:Input: $1.00/1MOutput Price:Output: $5.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

OpenAI
Higher GPQA score (78.0% vs 41.6%)
Higher MATH score (96.4% vs 69.4%)
Higher MGSM score (89.3% vs 85.6%)
Higher SWE-Bench Verified score (41.0% vs 40.6%)
Higher TAU-bench Airline score (50.0% vs 22.8%)
Higher TAU-bench Retail score (70.8% vs 51.0%)
Anthropic
Less expensive input tokens
Less expensive output tokens

Detailed Comparison

AI Model Comparison Table
Feature
OpenAI
o1
Anthropic
Claude 3.5 Haiku

FAQ

Common questions about o1 vs Claude 3.5 Haiku.

Which is better, o1 or Claude 3.5 Haiku?

o1 significantly outperforms across most benchmarks. o1 is made by OpenAI and Claude 3.5 Haiku is made by Anthropic. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does o1 compare to Claude 3.5 Haiku in benchmarks?

o1 scores GSM8k: 97.1%, MATH: 96.4%, GPQA Physics: 92.8%, MMLU: 91.8%, MGSM: 89.3%. Claude 3.5 Haiku scores HumanEval: 88.1%, MGSM: 85.6%, DROP: 83.1%, MATH: 69.4%, MMLU-Pro: 65.0%.

Is o1 cheaper than Claude 3.5 Haiku?

Claude 3.5 Haiku is 18.8x cheaper for input tokens. o1 costs $15.00/M input and $60.00/M output via azure. Claude 3.5 Haiku costs $0.80/M input and $4.00/M output via bedrock.

What are the context window sizes for o1 and Claude 3.5 Haiku?

o1 supports 200K tokens and Claude 3.5 Haiku supports 200K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between o1 and Claude 3.5 Haiku?

Key differences include input pricing ($15.00 vs $0.80/M). See the full comparison above for benchmark-by-benchmark results.

Who makes o1 and Claude 3.5 Haiku?

o1 is developed by OpenAI and Claude 3.5 Haiku is developed by Anthropic.

Related comparisons