Data points: 76
Model compare
The readout for GPT-5.3 Codex and GPT-5.4 Pro, before the detailed comparison sheet.
Weighted outcome: GPT-5.4 Pro. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
GPT-5.4 Pro
GPT-5.4 Pro has the higher weighted result; Model A / B score 20 to 80.
Evidence depth
76 data points
Includes 7 benchmark rows, 0 audit samples, and 6 provider examples.
Selection signal
Start with GPT-5.4 Pro
The charts below split 13 high-signal samples across speed, scores, and audit health.
Switch either side of this report to compare another model with the same LMSpeed data pipeline.
Select a different model to open a new comparison URL.
This report only uses LMSpeed data for GPT-5.3 Codex and GPT-5.4 Pro: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | GPT-5.3 Codex | GPT-5.4 Pro |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 20.0 pts | 80.0 pts |
| Benchmark category leads | 0 categories | 3 categories |
| Operational advantages | Cheapest input price, Free providers, Provider coverage | No data |
| Context window | 400K tokens | 1.1M tokens |
| Max output | 128K tokens | 128K tokens |
| Modalities | Input TextImageFile Output Text |
The overall result weights benchmark capability categories at 80% and price, API speed/latency, and availability at 20%. Recent test volume does not affect the winner, and missing benchmark categories are excluded.
| Model compare | GPT-5.3 Codex | GPT-5.4 Pro |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Released | Feb 2026 | Mar 2026 |
| Parameters | No data | No data |
| Tokenizer | GPT | GPT |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | openai/gpt-5.3-codex | openai/gpt-5.4-pro |
| References | No data | No data |
This report only uses LMSpeed data for GPT-5.3 Codex and GPT-5.4 Pro: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
GPT-5.3 Codex
GPT-5.3 Codex has these operational advantages: Cheapest input price, Free providers, Provider coverage.
GPT-5.4 Pro
GPT-5.4 Pro leads these benchmark categories: Agents, Reasoning, Knowledge.
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.
Avg. score
GPT-5.3 Codex
56.7
Avg. score
GPT-5.4 Pro
63
GPT-5.4 Pro leads by 7.0
GPT-5.3 Codex
GPT-5.4 Pro leads by 1.5
GPT-5.4 Pro leads by 6.9
GPT-5.4 Pro
No data
GPT-5.4 Pro
GPT-5.3 Codex
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
GPT-5.3 Codex
65.0
Rank #21/83 · confidence 1 · eval date 2026-02-05
GPT-5.4 Pro
winner82.0
Rank #1/83 · confidence 2 · eval date 2026-03-05
GPT-5.3 Codex
winner$1.75/M
Rank #122/163 · confidence 4
GPT-5.4 Pro
$30.00/M
Rank #161/163 · confidence 4
GPT-5.3 Codex
winner$4.81/M
Rank #134/163 · confidence 4
GPT-5.4 Pro
$67.50/M
Rank #162/163 · confidence 4
GPT-5.3 Codex
winner$14.00/M
Rank #135/163 · confidence 4
GPT-5.4 Pro
$180.00/M
Rank #162/163 · confidence 4
GPT-5.3 Codex
39.9%
Rank #12/186 · confidence 4
GPT-5.4 Pro
winner58.7%
Rank #1/186 · confidence 2 · eval date 2026-03-05
GPT-5.3 Codex
16.9
Rank #12/73 · confidence 1 · eval date 2026-02-05
GPT-5.4 Pro
winner30.0
Rank #3/73 · confidence 2 · eval date 2026-03-05
GPT-5.3 Codex
64.1
Rank #22/52 · confidence 1 · eval date 2026-02-05
GPT-5.4 Pro
winner81.6
Rank #10/52 · confidence 2 · eval date 2026-03-05
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GPT-5.3 Codex | GPT-5.4 Pro |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | GPT-5.3 Codex | GPT-5.4 Pro |
|---|---|---|
10 tests | GPT-5.3 Codex speed / latency 201 tok/s / 2135ms input / output No data | GPT-5.4 Pro speed / latency N/A / N/A input / output No data |
5 tests | GPT-5.3 Codex speed / latency 21 tok/s / 2445ms input / output No data | GPT-5.4 Pro speed / latency N/A / N/A input / output No data |
5 tests | GPT-5.3 Codex speed / latency 45 tok/s / 6276ms input / output No data | GPT-5.4 Pro speed / latency N/A / N/A input / output No data |
5 tests | GPT-5.3 Codex speed / latency 53 tok/s / 3889ms input / output No data | GPT-5.4 Pro speed / latency N/A / N/A input / output No data |
0 tests | GPT-5.3 Codex speed / latency N/A / N/A input / output No data | GPT-5.4 Pro speed / latency N/A / N/A input / output No data |
GPT-5.3 Codex gpt-5.3-codex-2026-02-24 speed / latency No data input / output $0/request | GPT-5.4 Pro gpt-5.4-pro speed / latency No data input / output $0/request |
Weighted outcome: GPT-5.4 Pro. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Input
Output
| Features | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
