Data points: 104
Model compare
The readout for GPT-5.2 and GPT-5.2 Codex, before the detailed comparison sheet.
Weighted outcome: GPT-5.2 Codex. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
GPT-5.2 Codex
GPT-5.2 Codex has the higher weighted result; Model A / B score 36 to 64.
Evidence depth
104 data points
Includes 20 benchmark rows, 0 audit samples, and 6 provider examples.
Selection signal
Start with GPT-5.2 Codex
The charts below split 26 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-5.2 and GPT-5.2 Codex: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | GPT-5.2 | GPT-5.2 Codex |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 36.0 pts | 64.0 pts |
| Benchmark category leads | 1 categories | 4 categories |
| Operational advantages | Cheapest input price, Average speed, First-token latency, Free providers, Provider coverage | No data |
| Context window | 400K tokens | 400K tokens |
| Max output | 128K tokens | 128K tokens |
| Modalities | Input FileImageText 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-5.2 | GPT-5.2 Codex |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Released | Dec 2025 | Jan 2026 |
| Parameters | No data | No data |
| Tokenizer | GPT | GPT |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | openai/gpt-5.2 | openai/gpt-5.2-codex |
| References | No data | No data |
This report only uses LMSpeed data for GPT-5.2 and GPT-5.2 Codex: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
GPT-5.2
GPT-5.2 is stronger in benchmark categories (Knowledge) and operational dimensions (Cheapest input price, Average speed, First-token latency, Free providers, Provider coverage).
GPT-5.2 Codex
GPT-5.2 Codex leads these benchmark categories: Agents, Coding, Reasoning, Instruction following.
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-5.2
52.8
Avg. score
GPT-5.2 Codex
55.5
GPT-5.2 Codex leads by 3.4
GPT-5.2 Codex leads by 1.8
GPT-5.2 Codex leads by 5.1
GPT-5.2 leads by 5.0
GPT-5.2
No data
GPT-5.2
GPT-5.2 Codex leads by 0.9
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
GPT-5.2
$1.75/M
Rank #120/162 · confidence 4
GPT-5.2 Codex
$1.75/M
Rank #120/162 · confidence 4
GPT-5.2
$4.81/M
Rank #132/162 · confidence 4
GPT-5.2 Codex
$4.81/M
Rank #132/162 · confidence 4
GPT-5.2
$14.00/M
Rank #133/162 · confidence 4
GPT-5.2 Codex
$14.00/M
Rank #133/162 · confidence 4
GPT-5.2
72.7
Rank #13/89 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
winner75.7
Rank #1/89 · confidence 1 · eval date 2025-12-18
GPT-5.2
winner11.6
Rank #20/73 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
8.7
Rank #26/73 · confidence 1 · eval date 2025-12-18
GPT-5.2
71.2%
Rank #110/188 · confidence 4
GPT-5.2 Codex
winner89.9%
Rank #21/188 · confidence 4
GPT-5.2
7.3%
Rank #109/187 · confidence 4
GPT-5.2 Codex
winner33.5%
Rank #24/187 · confidence 4
GPT-5.2
40.4%
Rank #64/185 · confidence 4
GPT-5.2 Codex
winner54.6%
Rank #6/185 · confidence 4
GPT-5.2
winner53.5
Rank #6/33 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
37.9
Rank #11/33 · confidence 1 · eval date 2025-12-18
GPT-5.2
52.1
Rank #18/96 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
winner54.6
Rank #8/96 · confidence 1 · eval date 2025-12-18
GPT-5.2
52.2
Rank #34/65 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
winner59.2
Rank #17/65 · confidence 1 · eval date 2025-12-18
GPT-5.2
winner43.8
Rank #16/90 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
40.7
Rank #20/90 · confidence 1 · eval date 2025-12-18
GPT-5.2
winner90.3
Rank #19/96 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
89.9
Rank #22/96 · confidence 1 · eval date 2025-12-18
GPT-5.2
winner35.4
Rank #21/96 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
33.5
Rank #24/96 · confidence 1 · eval date 2025-12-18
GPT-5.2
winner42.2
Rank #22/99 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
40.1
Rank #29/99 · confidence 1 · eval date 2025-12-18
GPT-5.2
winner79.7
Rank #39/90 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
72.8
Rank #53/90 · confidence 1 · eval date 2025-12-18
GPT-5.2
75.4
Rank #21/86 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
winner77.6
Rank #8/86 · confidence 1 · eval date 2025-12-18
GPT-5.2
winner34.3
Rank #7/20 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
26.0
Rank #12/20 · confidence 1 · eval date 2025-12-18
GPT-5.2
46.5
Rank #29/50 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
winner51.8
Rank #19/50 · confidence 1 · eval date 2025-12-18
GPT-5.2
84.8
Rank #44/84 · confidence 3 · eval date 2025-12-11
GPT-5.2 Codex
winner92.1
Rank #30/84 · confidence 1 · eval date 2025-12-18
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GPT-5.2 | GPT-5.2 Codex |
|---|---|---|
| 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-5.2 | GPT-5.2 Codex |
|---|---|---|
15 tests | GPT-5.2 speed / latency 56 tok/s / 1798ms input / output No data | GPT-5.2 Codex speed / latency N/A / N/A input / output No data |
15 tests | GPT-5.2 speed / latency 52 tok/s / 2671ms input / output No data | GPT-5.2 Codex speed / latency N/A / N/A input / output No data |
10 tests | GPT-5.2 speed / latency 51 tok/s / 2715ms input / output No data | GPT-5.2 Codex speed / latency 52 tok/s / 2410ms input / output No data |
10 tests | GPT-5.2 speed / latency 60 tok/s / 3331ms input / output No data | GPT-5.2 Codex speed / latency 55 tok/s / 5209ms input / output No data |
5 tests | GPT-5.2 speed / latency 64 tok/s / 3553ms input / output No data | GPT-5.2 Codex speed / latency N/A / N/A input / output No data |
GPT-5.2 gpt-5.2 speed / latency No data input / output $0/request | GPT-5.2 Codex gpt-5.2-codex speed / latency No data input / output $0/request |
Weighted outcome: GPT-5.2 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 inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
