The AI arena is free today

Open Superagent

GPT-5.2 Codex vs Step 3.7 Flash

GPT-5.2 Codex and Step 3.7 Flash are closely matched at 34.4 and 30.2 on the LLM Stats Score. Step 3.7 Flash is 11.0x cheaper per token.

OpenAI · StepFun · Updated for 2026

Which is better?

GPT-5.2 Codex and Step 3.7 Flash are closely matched on the overall LLM Stats Score at 34.4 and 30.2.

In the 1 individual benchmarks reported for both models, GPT-5.2 Codex wins 1; this is a narrower head-to-head signal than the composite indexes.

On price, Step 3.7 Flash is roughly 11.0x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

GPT-5.2 Codex also accepts a larger context window (400,000 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-5.2 Codex

  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • you process long inputs — it offers a 400,000 token context window

Choose Step 3.7 Flash

  • cost matters — it's about 11.0x cheaper per token
  • you want the most recent training data — it shipped Jun 2026
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Core performance indexes
34.4
#91
30.2
#120
34.7
#85
30.2
#117
25.1
#71
19.9
#99
19.1
#66
13.5
#92
Cost, coverage & limits
Benchmark wins
1 of 1
0 of 1
Input price
$1.75 / M
$0.20 / M
Output price
$14.00 / M
$1.15 / M
Context window
400,000
262,144

Individual benchmarks

3 reported for GPT-5.2 Codex · 4 for Step 3.7 Flash

1 shared

GPT-5.2 Codex outperforms in 1 benchmarks (SWE-Bench Pro), while Step 3.7 Flash is better at 0 benchmarks.

GPT-5.2 Codex significantly outperforms across most benchmarks.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Step 3.7 Flash costs less

For input processing, GPT-5.2 Codex ($1.75/1M tokens) is 8.8x more expensive than Step 3.7 Flash ($0.20/1M tokens).

For output processing, GPT-5.2 Codex ($14.00/1M tokens) is 12.2x more expensive than Step 3.7 Flash ($1.15/1M tokens).

In conclusion, GPT-5.2 Codex is more expensive than Step 3.7 Flash.*

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

Lowest available price from all providers
Sun Sep 20 2026 • llm-stats.com
OpenAI
GPT-5.2 Codex
Input tokens$1.75
Output tokens$14.00
Best providerOpenAI
StepFun
Step 3.7 Flash
Input tokens$0.20
Output tokens$1.15
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

GPT-5.2 Codex accepts 400,000 input tokens compared to Step 3.7 Flash's 262,144 tokens. Step 3.7 Flash can generate longer responses up to 262,144 tokens, while GPT-5.2 Codex is limited to 128,000 tokens.

OpenAI
GPT-5.2 Codex
Input400,000 tokens
Output128,000 tokens
StepFun
Step 3.7 Flash
Input262,144 tokens
Output262,144 tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both GPT-5.2 Codex and Step 3.7 Flash support multimodal inputs.

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

GPT-5.2 Codex

Text
Images
Audio
Video

Step 3.7 Flash

Text
Images
Audio
Video

License

Usage and distribution terms

GPT-5.2 Codex is licensed under a proprietary license, while Step 3.7 Flash uses Apache 2.0.

License differences may affect how you can use these models in commercial or open-source projects.

GPT-5.2 Codex

Proprietary

Closed source

Step 3.7 Flash

Apache 2.0

Open weights

Release Timeline

When each model was launched

GPT-5.2 Codex was released on 2026-01-14, while Step 3.7 Flash was released on 2026-06-10.

Step 3.7 Flash is 5 months newer than GPT-5.2 Codex.

GPT-5.2 Codex

Jan 14, 2026

8 months ago

Step 3.7 Flash

Jun 10, 2026

3 months ago

4mo 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-5.2 Codex is available from OpenAI. Step 3.7 Flash is available from DeepInfra.

GPT-5.2 Codex

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

Step 3.7 Flash

deepinfra logo
Deepinfra
Input Price:Input: $0.20/1MOutput Price:Output: $1.15/1M
* 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 GPT-5.2 Codex and Step 3.7 Flash side-by-side, then vote on the output you prefer.

GPT-5.2 Codex
✓ Preferred
Step 3.7 Flash
Open in Playground

FAQ

Common questions about GPT-5.2 Codex vs Step 3.7 Flash.

Which is better, GPT-5.2 Codex or Step 3.7 Flash?

GPT-5.2 Codex and Step 3.7 Flash are closely matched on the LLM Stats Score at 34.4 and 30.2. GPT-5.2 Codex is made by OpenAI and Step 3.7 Flash is made by StepFun. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does GPT-5.2 Codex compare to Step 3.7 Flash in benchmarks?

GPT-5.2 Codex scores LiveBench: 74.3%, Terminal-Bench 2.0: 64.0%, SWE-Bench Pro: 56.4%. Step 3.7 Flash scores Terminal-Bench 2.1: 59.5%, SWE-Bench Pro: 56.3%, Humanity's Last Exam (with tools, text-only): 47.2%, GDPval: 45.8%.

Is GPT-5.2 Codex cheaper than Step 3.7 Flash?

Step 3.7 Flash is 8.8x cheaper for input tokens. GPT-5.2 Codex costs $1.75/M input and $14.00/M output via openai. Step 3.7 Flash costs $0.20/M input and $1.15/M output via deepinfra.

What are the context window sizes for GPT-5.2 Codex and Step 3.7 Flash?

GPT-5.2 Codex supports 400K tokens and Step 3.7 Flash supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between GPT-5.2 Codex and Step 3.7 Flash?

Key differences include LLM Stats Score (34.4 vs 30.2), context window (400K vs 262K), input pricing ($1.75 vs $0.20/M), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT-5.2 Codex and Step 3.7 Flash?

GPT-5.2 Codex is developed by OpenAI and Step 3.7 Flash is developed by StepFun.