Data points: 85
The readout for GPT-5.2 Codex and GPT-5.4, before the detailed comparison sheet.
Decision read
GPT-5.4
GPT-5.4 currently has the stronger profile, with verified wins split 2 to 4.
Evidence depth
85 data points
Includes 8 benchmark rows, 1 audit samples, and 8 provider examples.
Selection signal
Start with GPT-5.4
The charts below split 17 high-signal samples across speed, scores, and audit health.
Model compare GPT-5.2 Codex vs GPT-5.4gpt-5-2-codex-vs-gpt-5-4 | Model A GPT-5.2 Codex | Model B GPT-5.4 |
|---|---|---|
| Overall leader | Contender | Leading |
| Verified metric wins | 2 wins | 4 wins |
| Where it leads | Average speed, First-token latency | Cheapest input price, Free providers, Provider coverage, Recent tests |
| Model metadata | GPT-5.2 Codex exposes 400K tokens; notable signals: Text input, Image input, Text output, Tool calling. | GPT-5.4 exposes 1.1M tokens; notable signals: Text input, Image input, File input, Text output. |
| Developer | OpenAI | OpenAI |
| Context window | 400K tokens | 1.1M tokens |
| Max output | 128K tokens | 128K tokens |
| Released | Jan 2026 | Mar 2026 |
| Modalities | Input TextImage Output Text | Input TextImageFile Output Text |
| Features | Text inputImage inputText outputTool callingStructured outputsJSON modeReasoning | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning |
| Parameters | No data | No data |
| Tokenizer | GPT | GPT |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | openai/gpt-5.2-codex | openai/gpt-5.4 |
| References | No data | No data |
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
| Metric | GPT-5.2 Codex | GPT-5.4 |
|---|---|---|
| GPQA | 89.9%#10 | 92.0%#3 |
| SciCode | 54.6%#5 | 56.6%#3 |
| HLE | 33.5%#11 | 41.6%#4 |
| Time to first answer token | 1.17 s#27 | 134.24 s#111 |
| Input price | $1.75/M#35 | $2.50/M#37 |
| Output speed | 125.5 tok/s#40 | 92.4 tok/s#56 |
| Output price | $14.00/M#43 | $15.00/M#44 |
| Time to first token | 1.17 s#44 | 134.24 s#110 |
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GPT-5.2 Codex | GPT-5.4 |
|---|---|---|
钠 APIWinner: GPT-5.4 | GPT-5.2 Codex gpt-5.2-codex No audit yet | GPT-5.4 gpt-5.4 Audit score 90 1008476100 |
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | GPT-5.2 Codex | GPT-5.4 |
|---|---|---|
Mars HK100 tests | GPT-5.2 Codex speed / latency N/A / N/A input / output No data | GPT-5.4 speed / latency 57 tok/s / 3556ms input / output No data |
天宫造物50 tests | GPT-5.2 Codex speed / latency N/A / N/A input / output No data | GPT-5.4 speed / latency 50 tok/s / 7305ms input / output No data |
巨量API44 tests | GPT-5.2 Codex speed / latency 67 tok/s / 4708ms input / output No data | GPT-5.4 speed / latency 43 tok/s / 12778ms input / output No data |
Sub2API20 tests | GPT-5.2 Codex speed / latency N/A / N/A input / output No data | GPT-5.4 speed / latency 51 tok/s / 4032ms input / output No data |
Sub2API20 tests | GPT-5.2 Codex speed / latency N/A / N/A input / output No data | GPT-5.4 speed / latency 34 tok/s / 1748ms input / output No data |
GPT-5.2 Codex gpt-5.2-codex speed / latency No data input / output $0/M / $0/M | GPT-5.4 gpt-5.4-openai-compact speed / latency No data input / output $75.00/M / $450.00/M | |
GPT-5.2 Codex gpt-5.2-codex speed / latency No data input / output $0.0038/M / $0.031/M | GPT-5.4 gpt-5.4 speed / latency No data input / output $0.068/M / $0.411/M | |
GPT-5.2 Codex gpt-5.2-codex-high speed / latency No data input / output $0.014/M / $0.014/M | GPT-5.4 gpt-5.4-openai-compact speed / latency No data input / output $4.11/M / $24.66/M |
This report only uses LMSpeed data for GPT-5.2 Codex and GPT-5.4: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Guidance | GPT-5.2 Codex | GPT-5.4 |
|---|---|---|
| When to choose each model | GPT-5.2 Codex GPT-5.2 Codex is stronger when you prioritize Average speed, First-token latency. | GPT-5.4 GPT-5.4 is stronger when you prioritize Cheapest input price, Free providers, Provider coverage, Recent tests. |
TL;DR: GPT-5.4 leads across 85 verifiable data points, including pricing, speed, latency, benchmarks, and provider examples.
Continue from GPT-5.2 Codex vs GPT-5.4 into nearby model comparisons with enough verified LMSpeed data.
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
