Model Comparison

GPT-5.4 vs Gemini 3.5 Flash

Gemini 3.5 Flash significantly outperforms across most benchmarks. Gemini 3.5 Flash is 1.7x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

9 benchmarks

GPT-5.4 outperforms in 2 benchmarks (ARC-AGI v2, SWE-Bench Pro), while Gemini 3.5 Flash is better at 7 benchmarks (Finance Agent, Humanity's Last Exam, MCP Atlas, MMMU-Pro, OSWorld-Verified, Terminal-Bench 2.0, Toolathlon).

Gemini 3.5 Flash significantly outperforms across most benchmarks.

Wed May 20 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Gemini 3.5 Flash costs less

For input processing, GPT-5.4 ($2.50/1M tokens) is 1.7x more expensive than Gemini 3.5 Flash ($1.50/1M tokens).

For output processing, GPT-5.4 ($15.00/1M tokens) is 1.7x more expensive than Gemini 3.5 Flash ($9.00/1M tokens).

In conclusion, GPT-5.4 is more expensive than Gemini 3.5 Flash.*

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

Lowest available price from all providers
Wed May 20 2026 • llm-stats.com
OpenAI
GPT-5.4
Input tokens$2.50
Output tokens$15.00
Best providerOpenAI
Google
Gemini 3.5 Flash
Input tokens$1.50
Output tokens$9.00
Best providerGoogle
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Gemini 3.5 Flash accepts 1,048,576 input tokens compared to GPT-5.4's 1,000,000 tokens. GPT-5.4 can generate longer responses up to 128,000 tokens, while Gemini 3.5 Flash is limited to 65,536 tokens.

OpenAI
GPT-5.4
Input1,000,000 tokens
Output128,000 tokens
Google
Gemini 3.5 Flash
Input1,048,576 tokens
Output65,536 tokens
Wed May 20 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both GPT-5.4 and Gemini 3.5 Flash support multimodal inputs.

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

GPT-5.4

Text
Images
Audio
Video

Gemini 3.5 Flash

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

Gemini 3.5 Flash

Proprietary

Closed source

Release Timeline

When each model was launched

GPT-5.4 was released on 2026-03-05, while Gemini 3.5 Flash was released on 2026-05-19.

Gemini 3.5 Flash is 3 months newer than GPT-5.4.

GPT-5.4

Mar 5, 2026

2 months ago

Gemini 3.5 Flash

May 19, 2026

1 days ago

2mo newer

Knowledge Cutoff

When training data ends

Gemini 3.5 Flash has a documented knowledge cutoff of 2026-01-31, while GPT-5.4's cutoff date is not specified.

We can confirm Gemini 3.5 Flash's training data extends to 2026-01-31, but cannot make a direct comparison without GPT-5.4's cutoff date.

GPT-5.4

—

Gemini 3.5 Flash

Jan 2026

Provider Availability

GPT-5.4 is available from OpenAI. Gemini 3.5 Flash is available from Google.

GPT-5.4

openai logo
OpenAI
Input Price:Input: $2.50/1MOutput Price:Output: $15.00/1M

Gemini 3.5 Flash

google logo
Google
Input Price:Input: $1.50/1MOutput Price:Output: $9.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

OpenAI
Higher ARC-AGI v2 score (73.3% vs 72.1%)
Higher SWE-Bench Pro score (57.7% vs 55.1%)
Google
Larger context window (1,048,576 tokens)
Less expensive input tokens
Less expensive output tokens
Higher Finance Agent score (57.9% vs 56.0%)
Higher Humanity's Last Exam score (40.2% vs 39.8%)
Higher MCP Atlas score (83.6% vs 67.2%)
Higher MMMU-Pro score (83.6% vs 81.2%)
Higher OSWorld-Verified score (78.4% vs 75.0%)
Higher Terminal-Bench 2.0 score (76.2% vs 75.1%)
Higher Toolathlon score (56.5% vs 54.6%)

Detailed Comparison

AI Model Comparison Table
Feature
OpenAI
GPT-5.4
Google
Gemini 3.5 Flash

FAQ

Common questions about GPT-5.4 vs Gemini 3.5 Flash.

Which is better, GPT-5.4 or Gemini 3.5 Flash?

Gemini 3.5 Flash significantly outperforms across most benchmarks. GPT-5.4 is made by OpenAI and Gemini 3.5 Flash is made by Google. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does GPT-5.4 compare to Gemini 3.5 Flash in benchmarks?

GPT-5.4 scores Tau2 Telecom: 98.9%, ARC-AGI: 93.7%, Graphwalks BFS <128k: 93.0%, GPQA: 92.8%, Graphwalks parents <128k: 89.8%. Gemini 3.5 Flash scores CharXiv-R: 84.2%, MCP Atlas: 83.6%, MMMU-Pro: 83.6%, OSWorld-Verified: 78.4%, Terminal-Bench 2.0: 76.2%.

Is GPT-5.4 cheaper than Gemini 3.5 Flash?

Gemini 3.5 Flash is 1.7x cheaper for input tokens. GPT-5.4 costs $2.50/M input and $15.00/M output via openai. Gemini 3.5 Flash costs $1.50/M input and $9.00/M output via google.

What are the context window sizes for GPT-5.4 and Gemini 3.5 Flash?

GPT-5.4 supports 1.0M tokens and Gemini 3.5 Flash supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between GPT-5.4 and Gemini 3.5 Flash?

Key differences include context window (1.0M vs 1.0M), input pricing ($2.50 vs $1.50/M). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT-5.4 and Gemini 3.5 Flash?

GPT-5.4 is developed by OpenAI and Gemini 3.5 Flash is developed by Google.