GPT-5.4 vs Claude Sonnet 4.6 Comparison

Comparing GPT-5.4 and Claude Sonnet 4.6 across benchmarks, pricing, and capabilities.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

9 benchmarks

GPT-5.4 outperforms in 7 benchmarks (ARC-AGI v2, BrowseComp, GPQA, MCP Atlas, MMMU-Pro, Tau2 Telecom, Terminal-Bench 2.0), while Claude Sonnet 4.6 is better at 2 benchmarks (Finance Agent, Humanity's Last Exam).

GPT-5.4 significantly outperforms across most benchmarks.

Tue Mar 17 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Cost data unavailable.

Lowest available price from all providers
Tue Mar 17 2026 • llm-stats.com
OpenAI
GPT-5.4
Input tokens$2.50
Output tokens$15.00
Best providerOpenAI
Anthropic
Claude Sonnet 4.6
Input tokens$0.00
Output tokens$0.00
Best providerUnknown Organization
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Only GPT-5.4 specifies input context (1,000,000 tokens). Only GPT-5.4 specifies output context (128,000 tokens).

OpenAI
GPT-5.4
Input1,000,000 tokens
Output128,000 tokens
Anthropic
Claude Sonnet 4.6
Input- tokens
Output- tokens
Tue Mar 17 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both GPT-5.4 and Claude Sonnet 4.6 support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

GPT-5.4

Text
Images
Audio
Video

Claude Sonnet 4.6

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.

GPT-5.4

Proprietary

Closed source

Claude Sonnet 4.6

Proprietary

Closed source

Release Timeline

When each model was launched

GPT-5.4 was released on 2026-03-05, while Claude Sonnet 4.6 was released on 2026-02-17.

GPT-5.4 is 1 month newer than Claude Sonnet 4.6.

GPT-5.4

Mar 5, 2026

1 weeks ago

2w newer
Claude Sonnet 4.6

Feb 17, 2026

4 weeks 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

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

OpenAI
Larger context window (1,000,000 tokens)
Higher ARC-AGI v2 score (73.3% vs 58.3%)
Higher BrowseComp score (82.7% vs 74.7%)
Higher GPQA score (92.8% vs 89.9%)
Higher MCP Atlas score (67.2% vs 61.3%)
Higher MMMU-Pro score (81.2% vs 75.6%)
Higher Tau2 Telecom score (98.9% vs 97.9%)
Higher Terminal-Bench 2.0 score (75.1% vs 59.1%)
Anthropic
Higher Finance Agent score (63.3% vs 56.0%)
Higher Humanity's Last Exam score (49.0% vs 39.8%)

Detailed Comparison

AI Model Comparison Table
Feature
OpenAI
GPT-5.4
Anthropic
Claude Sonnet 4.6