Data points: 125
Model compare
The readout for GPT-5.3 Codex and GPT-5.4 Nano, before the detailed comparison sheet.
Weighted outcome: GPT-5.3 Codex. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
GPT-5.3 Codex
GPT-5.3 Codex has the higher weighted result; Model A / B score 78.7 to 21.3.
Evidence depth
125 data points
Includes 30 benchmark rows, 0 audit samples, and 6 provider examples.
Selection signal
Start with GPT-5.3 Codex
The charts below split 36 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 Nano: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | GPT-5.3 Codex | GPT-5.4 Nano |
|---|---|---|
| Overall leader | Leading | Contender |
| Weighted overall score | 78.7 pts | 21.3 pts |
| Benchmark category leads | 5 categories | 1 categories |
| Operational advantages | Cheapest input price, Free providers, Provider coverage | Average speed, First-token latency |
| Context window | 400K tokens | 400K tokens |
| Max output | 128K tokens | 128K tokens |
| Modalities | Input TextImageFile Output Text | Input |
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 Nano |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Released | Feb 2026 | Mar 2026 |
| Parameters | No data | No data |
| Tokenizer | GPT | GPT |
| Knowledge cutoff | No data | 2025-08-31 |
| OpenRouter ID | openai/gpt-5.3-codex | openai/gpt-5.4-nano |
| References | No data | No data |
This report only uses LMSpeed data for GPT-5.3 Codex and GPT-5.4 Nano: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
GPT-5.3 Codex
GPT-5.3 Codex is stronger in benchmark categories (Agents, Coding, Reasoning, Knowledge, Multimodal) and operational dimensions (Cheapest input price, Free providers, Provider coverage).
GPT-5.4 Nano
GPT-5.4 Nano is stronger in benchmark categories (Instruction following) and operational dimensions (Average speed, First-token latency).
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
59.6
Avg. score
GPT-5.4 Nano
47.5
GPT-5.3 Codex leads by 7.8
GPT-5.3 Codex leads by 7.4
GPT-5.3 Codex leads by 10.8
GPT-5.3 Codex leads by 11.6
GPT-5.4 Nano
GPT-5.3 Codex
GPT-5.3 Codex leads by 39.0
GPT-5.4 Nano leads by 0.2
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
GPT-5.3 Codex
winner82.0
Rank #11/127 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
60.0
Rank #50/127 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
95.6 tok/s
Rank #62/139 · confidence 4
GPT-5.4 Nano
winner161.8 tok/s
Rank #30/139 · confidence 4
GPT-5.3 Codex
69.67 s
Rank #128/139 · confidence 4
GPT-5.4 Nano
winner4.95 s
Rank #61/139 · confidence 4
GPT-5.3 Codex
69.67 s
Rank #132/139 · confidence 4
GPT-5.4 Nano
winner4.95 s
Rank #108/139 · confidence 4
GPT-5.3 Codex
$1.75/M
Rank #122/163 · confidence 4
GPT-5.4 Nano
winner$0.200/M
Rank #28/163 · confidence 4
GPT-5.3 Codex
$4.81/M
Rank #134/163 · confidence 4
GPT-5.4 Nano
winner$0.463/M
Rank #38/163 · confidence 4
GPT-5.3 Codex
$14.00/M
Rank #135/163 · confidence 4
GPT-5.4 Nano
winner$1.25/M
Rank #51/163 · confidence 4
GPT-5.3 Codex
winner87.4
Rank #4/70 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
29.1
Rank #58/70 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner74.0
Rank #5/89 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
66.0
Rank #40/89 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner91.5%
Rank #11/187 · confidence 4
GPT-5.4 Nano
81.7%
Rank #68/187 · confidence 4
GPT-5.3 Codex
winner16.9
Rank #12/73 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
9.3
Rank #22/73 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner39.9%
Rank #12/186 · confidence 4
GPT-5.4 Nano
26.5%
Rank #39/186 · confidence 4
GPT-5.3 Codex
winner61.8
Rank #4/33 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
26.1
Rank #16/33 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner87.0
Rank #6/100 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
66.1
Rank #47/100 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner53.0
Rank #9/85 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
42.4
Rank #27/85 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner53.2%
Rank #10/184 · confidence 4
GPT-5.4 Nano
46.9%
Rank #26/184 · confidence 4
GPT-5.3 Codex
winner53.2
Rank #14/96 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
46.9
Rank #33/96 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner89.0
Rank #4/92 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
67.5
Rank #39/92 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner51.8
Rank #8/90 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
25.4
Rank #54/90 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner39.9
Rank #11/96 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
26.5
Rank #39/96 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner91.5
Rank #12/96 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
81.7
Rank #57/96 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner44.3
Rank #16/99 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
38.2
Rank #36/99 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner86.9
Rank #23/90 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
73.6
Rank #51/90 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner91.5
Rank #2/81 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
54.0
Rank #60/81 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner78.5
Rank #14/57 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
65.4
Rank #44/57 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
75.4
Rank #21/86 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
winner75.9
Rank #16/86 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner77.3
Rank #9/45 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
46.3
Rank #40/45 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner64.7
Rank #15/21 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
39.0
Rank #21/21 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner77.5
Rank #21/95 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
48.8
Rank #55/95 · confidence 2 · eval date 2026-03-17
GPT-5.3 Codex
winner86.0
Rank #41/84 · confidence 1 · eval date 2026-02-05
GPT-5.4 Nano
76.0
Rank #58/84 · confidence 2 · eval date 2026-03-17
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GPT-5.3 Codex | GPT-5.4 Nano |
|---|---|---|
| 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 Nano |
|---|---|---|
14 tests | GPT-5.3 Codex speed / latency 252 tok/s / 2196ms input / output No data | GPT-5.4 Nano speed / latency N/A / N/A input / output No data |
10 tests | GPT-5.3 Codex speed / latency N/A / N/A input / output No data | GPT-5.4 Nano speed / latency 147 tok/s / 4365ms input / output No data |
10 tests | GPT-5.3 Codex speed / latency 201 tok/s / 2135ms input / output No data | GPT-5.4 Nano 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 Nano speed / latency N/A / N/A input / output No data |
5 tests | GPT-5.3 Codex speed / latency N/A / N/A input / output No data | GPT-5.4 Nano speed / latency 118 tok/s / 1397ms 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 Nano gpt-5.4-nano-2026-03-17 speed / latency No data input / output $0/request |
Weighted outcome: GPT-5.3 Codex. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Output
| Features | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
