Data points: 135
Model compare
The readout for GPT-5.3 Codex and GPT-5.4, before the detailed comparison sheet.
Weighted outcome: GPT-5.4. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
GPT-5.4
GPT-5.4 has the higher weighted result; Model A / B score 40 to 60.
Evidence depth
135 data points
Includes 28 benchmark rows, 3 audit samples, and 7 provider examples.
Selection signal
Start with GPT-5.4
The charts below split 38 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: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | GPT-5.3 Codex | GPT-5.4 |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 40.0 pts | 60.0 pts |
| Benchmark category leads | 2 categories | 3 categories |
| Operational advantages | Average speed, First-token latency | Cheapest input price, Free providers, Provider coverage |
| 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 |
|---|---|---|
| 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 |
| References | No data | No data |
This report only uses LMSpeed data for GPT-5.3 Codex and GPT-5.4: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
GPT-5.3 Codex
GPT-5.3 Codex is stronger in benchmark categories (Reasoning, Instruction following) and operational dimensions (Average speed, First-token latency).
GPT-5.4
GPT-5.4 is stronger in benchmark categories (Agents, Coding, Knowledge) and operational dimensions (Cheapest input price, Free providers, Provider coverage).
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
56.5
Avg. score
GPT-5.4
57.4
GPT-5.4 leads by 3.2
GPT-5.4 leads by 4.1
GPT-5.3 Codex leads by 3.8
GPT-5.4 leads by 4.9
GPT-5.4
No data
GPT-5.4
GPT-5.3 Codex leads by 0.6
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
GPT-5.3 Codex
64.0
Rank #22/84 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner67.0
Rank #19/84 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
winner$1.75/M
Rank #120/162 · confidence 4
GPT-5.4
$2.50/M
Rank #131/162 · confidence 4
GPT-5.3 Codex
winner$4.81/M
Rank #132/162 · confidence 4
GPT-5.4
$5.63/M
Rank #135/162 · confidence 4
GPT-5.3 Codex
winner$14.00/M
Rank #133/162 · confidence 4
GPT-5.4
$15.00/M
Rank #136/162 · confidence 4
GPT-5.3 Codex
74.0
Rank #6/89 · confidence 1 · eval date 2026-02-05
GPT-5.4
74.0
Rank #6/89 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
16.9
Rank #13/73 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner23.4
Rank #7/73 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
winner91.5%
Rank #12/188 · confidence 4
GPT-5.4
74.8%
Rank #96/188 · confidence 4
GPT-5.3 Codex
winner39.9%
Rank #13/187 · confidence 4
GPT-5.4
10.6%
Rank #91/187 · confidence 4
GPT-5.3 Codex
61.8
Rank #4/33 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner67.4
Rank #3/33 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
53.2
Rank #15/96 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner56.6
Rank #4/96 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
winner53.2%
Rank #11/185 · confidence 4
GPT-5.4
47.1%
Rank #24/185 · confidence 4
GPT-5.3 Codex
56.8
Rank #20/37 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner57.7
Rank #15/37 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
winner58.5
Rank #19/65 · confidence 1 · eval date 2026-02-05
GPT-5.4
42.4
Rank #53/65 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
39.9
Rank #12/96 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner41.6
Rank #8/96 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
winner51.8
Rank #8/90 · confidence 1 · eval date 2026-02-05
GPT-5.4
50.0
Rank #9/90 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
44.3
Rank #17/99 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner51.4
Rank #10/99 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
91.5
Rank #13/96 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner92.0
Rank #11/96 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
winner9.9
Rank #16/29 · confidence 1 · eval date 2026-02-05
GPT-5.4
5.7
Rank #18/29 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
86.9
Rank #22/90 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner88.6
Rank #18/90 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
winner78.5
Rank #15/57 · confidence 1 · eval date 2026-02-05
GPT-5.4
78.4
Rank #16/57 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
1187.0
Rank #46/66 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner1245.0
Rank #32/66 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
winner75.4
Rank #21/86 · confidence 1 · eval date 2026-02-05
GPT-5.4
73.9
Rank #24/86 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
57.5
Rank #13/50 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner64.9
Rank #4/50 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
33.7
Rank #8/20 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner38.9
Rank #4/20 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
64.7
Rank #15/21 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner75.0
Rank #7/21 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
winner77.3
Rank #10/46 · confidence 1 · eval date 2026-02-05
GPT-5.4
75.1
Rank #12/46 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
64.3
Rank #23/53 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner74.7
Rank #14/53 · confidence 3 · eval date 2026-03-05
GPT-5.3 Codex
86.0
Rank #41/84 · confidence 1 · eval date 2026-02-05
GPT-5.4
winner87.1
Rank #37/84 · confidence 3 · 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 |
|---|---|---|
Winner: GPT-5.4 | GPT-5.3 Codex gpt-5.3-codex No audit yet | GPT-5.4 gpt-5.4 Audit score 100 100100100100 |
Winner: GPT-5.4 | GPT-5.3 Codex gpt-5.3-codex No audit yet | GPT-5.4 gpt-5.4 Audit score 93 1008486100 |
Winner: GPT-5.4 | GPT-5.3 Codex gpt-5.3-codex-spark No audit yet | GPT-5.4 gpt-5.4 Audit score 83 727980100 |
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 |
|---|---|---|
125 tests | GPT-5.3 Codex speed / latency N/A / N/A input / output No data | GPT-5.4 speed / latency 49 tok/s / 6084ms input / output No data |
114 tests | GPT-5.3 Codex speed / latency 252 tok/s / 2196ms input / output No data | GPT-5.4 speed / latency 57 tok/s / 3556ms input / output No data |
55 tests | GPT-5.3 Codex speed / latency 38 tok/s / 4553ms input / output No data | GPT-5.4 speed / latency 49 tok/s / 5435ms input / output No data |
50 tests | GPT-5.3 Codex speed / latency N/A / N/A input / output No data | GPT-5.4 speed / latency 50 tok/s / 7305ms input / output No data |
35 tests | GPT-5.3 Codex speed / latency N/A / N/A input / output No data | GPT-5.4 speed / latency 50 tok/s / 2467ms input / output No data |
GPT-5.3 Codex gpt-5.3-codex-openai-compact speed / latency No data input / output $0/M/$0/M | GPT-5.4 gpt-5.4 speed / latency No data input / output $0/M | |
GPT-5.3 Codex gpt-5.3-codex-spark speed / latency No data input / output $0/request | GPT-5.4 gpt-5.4 speed / latency No data input / output $0/request |
Weighted outcome: GPT-5.4. 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 |
|---|
