The AI arena is free today

Open Superagent

GPT-5.3 Codex vs Mercury 3

GPT-5.3 Codex and Mercury 3 are closely matched at 36.3 and 36.1 on the LLM Stats Score. Mercury 3 is 29.6x cheaper per token.

OpenAI · Inception · Updated for 2026

Which is better?

GPT-5.3 Codex and Mercury 3 are closely matched on the overall LLM Stats Score at 36.3 and 36.1.

On price, Mercury 3 is roughly 29.6x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Mercury 3 also accepts a larger context window (1,000,000 input tokens), making it the stronger choice for long documents and large codebases.

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

Choose GPT-5.3 Codex

  • you want predictable pricing at $1.75/M input and $14.00/M output

Choose Mercury 3

  • cost matters — it's about 29.6x cheaper per token
  • you process long inputs — it offers a 1,000,000 token context window
  • you want the most recent training data — it shipped Oct 2026

At a glance

The differences that matter most.

GPT-5.3 Codex
OpenAI
Mercury 3
Inception
Core performance indexes
LLM Stats Score
36.3
#96
36.1
#98
Reasoning
37.0
#87
34.8
#103
Coding
29.5
#64
21.5
#105
Agents
22.7
#76
19.4
#84
Cost, coverage & limits
Benchmark wins
—
—
Input price
$1.75 / M
$0.10 / M
Output price
$14.00 / M
$0.35 / M
Context window
400,000
1,000,000

Individual benchmarks

6 reported for GPT-5.3 Codex · 12 for Mercury 3

No common benchmarks found

GPT-5.3 Codex and Mercury 3don't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Mercury 3 costs less

For input processing, GPT-5.3 Codex ($1.75/1M tokens) is 17.5x more expensive than Mercury 3 ($0.10/1M tokens).

For output processing, GPT-5.3 Codex ($14.00/1M tokens) is 40.0x more expensive than Mercury 3 ($0.35/1M tokens).

In conclusion, GPT-5.3 Codex is more expensive than Mercury 3.*

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

Lowest available price from all providers
Thu Oct 22 2026 • llm-stats.com
OpenAI
GPT-5.3 Codex
Input tokens$1.75
Output tokens$14.00
Best providerOpenAI
Inception
Mercury 3
Input tokens$0.10
Output tokens$0.35
Best providerInception
Notice missing or incorrect data?

Context Window

Maximum input and output token capacity

Mercury 3 accepts 1,000,000 input tokens compared to GPT-5.3 Codex's 400,000 tokens. Mercury 3 can generate longer responses up to 131,072 tokens, while GPT-5.3 Codex is limited to 128,000 tokens.

OpenAI
GPT-5.3 Codex
Input400,000 tokens
Output128,000 tokens
Inception
Mercury 3
Input1,000,000 tokens
Output131,072 tokens
Thu Oct 22 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

GPT-5.3 Codex supports multimodal inputs, whereas Mercury 3 does not.

GPT-5.3 Codex can handle both text and other forms of data like images, making it suitable for multimodal applications.

GPT-5.3 Codex

Text
Images
Audio
Video

Mercury 3

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-5.3 Codex

Proprietary

Closed source

Mercury 3

Proprietary

Closed source

Release Timeline

When each model was launched

GPT-5.3 Codex was released on 2026-02-05, while Mercury 3 was released on 2026-10-19.

Mercury 3 is 9 months newer than GPT-5.3 Codex.

GPT-5.3 Codex

Feb 5, 2026

8 months ago

Mercury 3

Oct 19, 2026

0 days ago

8mo newer

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

GPT-5.3 Codex is available from OpenAI. Mercury 3 is available from Inception.

GPT-5.3 Codex

openai logo
OpenAI
Input Price:Input: $1.75/1MOutput Price:Output: $14.00/1M

Mercury 3

inception logo
Inception
Input Price:Input: $0.10/1MOutput Price:Output: $0.35/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against GPT-5.3 Codex and Mercury 3 side-by-side, then vote on the output you prefer.

GPT-5.3 Codex
✓ Preferred
Mercury 3
Open in Playground

FAQ

Common questions about GPT-5.3 Codex vs Mercury 3.

Which is better, GPT-5.3 Codex or Mercury 3?

GPT-5.3 Codex and Mercury 3 are closely matched on the LLM Stats Score at 36.3 and 36.1. GPT-5.3 Codex is made by OpenAI and Mercury 3 is made by Inception. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does GPT-5.3 Codex compare to Mercury 3 in benchmarks?

GPT-5.3 Codex scores SWE-Lancer (IC-Diamond subset): 81.4%, Cybersecurity CTFs: 77.6%, Terminal-Bench 2.0: 77.3%, LiveBench: 72.8%, OSWorld-Verified: 64.7%. Mercury 3 scores GPQA: 89.2%, AA-LCR: 77.7%, IFBench: 76.8%, MRCR v2: 75.5%, DeepSearchQA: 71.3%.

Is GPT-5.3 Codex cheaper than Mercury 3?

Mercury 3 is 17.5x cheaper for input tokens. GPT-5.3 Codex costs $1.75/M input and $14.00/M output via openai. Mercury 3 costs $0.10/M input and $0.35/M output via inception.

What are the context window sizes for GPT-5.3 Codex and Mercury 3?

GPT-5.3 Codex supports 400K tokens and Mercury 3 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-5.3 Codex and Mercury 3?

Key differences include LLM Stats Score (36.3 vs 36.1), context window (400K vs 1.0M), input pricing ($1.75 vs $0.10/M), multimodal support (yes vs no). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT-5.3 Codex and Mercury 3?

GPT-5.3 Codex is developed by OpenAI and Mercury 3 is developed by Inception.

Related comparisons