The AI arena is free today

Open Superagent

Claude 3.5 Haiku vs Claude 3 Opus

Claude 3.5 Haiku and Claude 3 Opus are closely matched at 5.3 and 10.0 on the LLM Stats Score. Claude 3.5 Haiku is 18.8x cheaper per token.

Anthropic · Anthropic · Updated for 2026

Which is better?

Claude 3.5 Haiku and Claude 3 Opus are closely matched on the overall LLM Stats Score at 5.3 and 10.0.

In the 6 individual benchmarks reported for both models, Claude 3 Opus wins 4; this is a narrower head-to-head signal than the composite indexes.

On price, Claude 3.5 Haiku is roughly 18.8x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

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

Choose Claude 3.5 Haiku

  • cost matters — it's about 18.8x cheaper per token
  • you want the most recent training data — it shipped Oct 2024

Choose Claude 3 Opus

  • you value its reported benchmark strengths — it wins 4 of 6 exact shared results

At a glance

The differences that matter most.

Claude 3.5 Haiku
Anthropic
Claude 3 Opus
Anthropic
Core performance indexes
LLM Stats Score
5.3
#287
10.0
#256
Reasoning
5.5
#283
9.9
#249
Coding
4.4
#203
5.2
#196
Cost, coverage & limits
Benchmark wins
2 of 6
4 of 6
Input price
$0.80 / M
$15.00 / M
Output price
$4.00 / M
$75.00 / M
Context window
200,000
200,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Claude 3.5 Haiku
Claude 3 Opus
Math
10.8#242
16.4#199
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

9 reported for Claude 3.5 Haiku · 11 for Claude 3 Opus

6 shared

Claude 3.5 Haiku outperforms in 2 benchmarks (HumanEval, MATH), while Claude 3 Opus is better at 3 benchmarks (GPQA, MGSM, MMLU-Pro).

Claude 3 Opus has a slight edge in benchmark performance.

Mon Sep 07 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Claude 3.5 Haiku costs less

For input processing, Claude 3.5 Haiku ($0.80/1M tokens) is 18.8x cheaper than Claude 3 Opus ($15.00/1M tokens).

For output processing, Claude 3.5 Haiku ($4.00/1M tokens) is 18.8x cheaper than Claude 3 Opus ($75.00/1M tokens).

In conclusion, Claude 3 Opus is more expensive than Claude 3.5 Haiku.*

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

Lowest available price from all providers
Mon Sep 07 2026 • llm-stats.com
Anthropic
Claude 3.5 Haiku
Input tokens$0.80
Output tokens$4.00
Best providerAWS Bedrock
Anthropic
Claude 3 Opus
Input tokens$15.00
Output tokens$75.00
Best providerAnthropic
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. Both models can generate responses up to 200,000 tokens.

Anthropic
Claude 3.5 Haiku
Input200,000 tokens
Output200,000 tokens
Anthropic
Claude 3 Opus
Input200,000 tokens
Output200,000 tokens
Mon Sep 07 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Claude 3 Opus supports multimodal inputs, whereas Claude 3.5 Haiku does not.

Claude 3 Opus can handle both text and other forms of data like images, making it suitable for multimodal applications.

Claude 3.5 Haiku

Text
Images
Audio
Video

Claude 3 Opus

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

Claude 3.5 Haiku

Proprietary

Closed source

Claude 3 Opus

Proprietary

Closed source

Release Timeline

When each model was launched

Claude 3.5 Haiku was released on 2024-10-22, while Claude 3 Opus was released on 2024-02-29.

Claude 3.5 Haiku is 8 months newer than Claude 3 Opus.

Claude 3.5 Haiku

Oct 22, 2024

1.9 years ago

7mo newer
Claude 3 Opus

Feb 29, 2024

2.5 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

Claude 3.5 Haiku is available from Bedrock, Google, Anthropic. Claude 3 Opus is available from Anthropic, Bedrock, Google.

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

Claude 3 Opus

anthropic logo
Anthropic
Input Price:Input: $15.00/1MOutput Price:Output: $75.00/1M
bedrock logo
AWS Bedrock
Input Price:Input: $15.00/1MOutput Price:Output: $75.00/1M
google logo
Google
Input Price:Input: $15.00/1MOutput Price:Output: $75.00/1M
* 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 Claude 3.5 Haiku and Claude 3 Opus side-by-side, then vote on the output you prefer.

Claude 3.5 Haiku
✓ Preferred
Claude 3 Opus
Open in Playground

FAQ

Common questions about Claude 3.5 Haiku vs Claude 3 Opus.

Which is better, Claude 3.5 Haiku or Claude 3 Opus?

Claude 3.5 Haiku and Claude 3 Opus are closely matched on the LLM Stats Score at 5.3 and 10.0. Claude 3.5 Haiku is made by Anthropic and Claude 3 Opus is made by Anthropic. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Claude 3.5 Haiku compare to Claude 3 Opus in benchmarks?

Claude 3.5 Haiku scores HumanEval: 88.1%, MGSM: 85.6%, DROP: 83.1%, MATH: 69.4%, MMLU-Pro: 65.0%. Claude 3 Opus scores ARC-C: 96.4%, HellaSwag: 95.4%, GSM8k: 95.0%, MGSM: 90.7%, BIG-Bench Hard: 86.8%.

Is Claude 3.5 Haiku cheaper than Claude 3 Opus?

Claude 3.5 Haiku is 18.8x cheaper for input tokens. Claude 3.5 Haiku costs $0.80/M input and $4.00/M output via bedrock. Claude 3 Opus costs $15.00/M input and $75.00/M output via anthropic.

What are the context window sizes for Claude 3.5 Haiku and Claude 3 Opus?

Claude 3.5 Haiku supports 200K tokens and Claude 3 Opus 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 Claude 3.5 Haiku and Claude 3 Opus?

Key differences include LLM Stats Score (5.3 vs 10.0), input pricing ($0.80 vs $15.00/M), multimodal support (no vs yes). See the full comparison above for benchmark-by-benchmark results.

Related comparisons