Data points: 112
Model compare
The readout for GPT-5.3 Codex and Inkling, 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 84 to 16.
Evidence depth
112 data points
Includes 25 benchmark rows, 0 audit samples, and 5 provider examples.
Selection signal
Start with GPT-5.3 Codex
The charts below split 30 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 Inkling: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | GPT-5.3 Codex | Inkling |
|---|---|---|
| Overall leader | Leading | Contender |
| Weighted overall score | 84.0 pts | 16.0 pts |
| Benchmark category leads | 4 categories | 1 categories |
| Operational advantages | Cheapest input price, Free providers, Provider coverage | No data |
| Context window | 400K tokens | 1.0M tokens |
| Max output | 128K tokens | No data |
| 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 | Inkling |
|---|---|---|
| Developer | OpenAI | Thinking Machines |
| Released | Feb 2026 | Jul 2026 |
| Parameters | No data | No data |
| Tokenizer | GPT | Other |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | openai/gpt-5.3-codex | thinkingmachines/inkling |
| References | No data | No data |
This report only uses LMSpeed data for GPT-5.3 Codex and Inkling: 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) and operational dimensions (Cheapest input price, Free providers, Provider coverage).
Inkling
Inkling leads these benchmark categories: 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-5.3 Codex
56.5
Avg. score
Inkling
53.5
GPT-5.3 Codex leads by 3.0
GPT-5.3 Codex leads by 9.0
GPT-5.3 Codex leads by 5.9
GPT-5.3 Codex leads by 1.3
Inkling
No data
Inkling
Inkling leads by 1.9
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
GPT-5.3 Codex
winner64.0
Rank #25/90 · confidence 1 · eval date 2026-02-05
Inkling
60.0
Rank #34/90 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner128.0 tok/s
Rank #29/73 · confidence 4
Inkling
85.3 tok/s
Rank #42/73 · confidence 4
GPT-5.3 Codex
50.42 s
Rank #64/73 · confidence 4
Inkling
winner25.59 s
Rank #49/73 · confidence 4
GPT-5.3 Codex
50.42 s
Rank #70/73 · confidence 4
Inkling
winner2.13 s
Rank #54/73 · confidence 4
GPT-5.3 Codex
$14.00/M
Rank #139/169 · confidence 4
Inkling
winner$4.68/M
Rank #107/169 · confidence 4
GPT-5.3 Codex
$4.81/M
Rank #138/169 · confidence 4
Inkling
winner$2.57/M
Rank #112/169 · confidence 4
GPT-5.3 Codex
winner$1.75/M
Rank #125/169 · confidence 4
Inkling
$1.87/M
Rank #128/169 · confidence 4
GPT-5.3 Codex
winner74.0
Rank #6/94 · confidence 1 · eval date 2026-02-05
Inkling
63.3
Rank #54/94 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner16.9
Rank #14/77 · confidence 1 · eval date 2026-02-05
Inkling
5.4
Rank #36/77 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner91.5%
Rank #14/194 · confidence 4
Inkling
87.2%
Rank #37/194 · confidence 4
GPT-5.3 Codex
winner39.9%
Rank #15/193 · confidence 4
Inkling
29.7%
Rank #36/193 · confidence 4
GPT-5.3 Codex
winner85.0
Rank #6/45 · confidence 1 · eval date 2026-02-05
Inkling
77.6
Rank #20/45 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner53.2%
Rank #13/191 · confidence 4
Inkling
46.1%
Rank #36/191 · confidence 4
GPT-5.3 Codex
winner53.2
Rank #17/101 · confidence 1 · eval date 2026-02-05
Inkling
46.1
Rank #40/101 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner58.5
Rank #21/71 · confidence 1 · eval date 2026-02-05
Inkling
48.9
Rank #47/71 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner56.8
Rank #23/42 · confidence 1 · eval date 2026-02-05
Inkling
54.3
Rank #32/42 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner51.8
Rank #9/95 · confidence 1 · eval date 2026-02-05
Inkling
40.0
Rank #26/95 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner39.9
Rank #14/101 · confidence 1 · eval date 2026-02-05
Inkling
29.7
Rank #34/101 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner91.5
Rank #15/101 · confidence 1 · eval date 2026-02-05
Inkling
87.2
Rank #40/101 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner9.9
Rank #19/34 · confidence 1 · eval date 2026-02-05
Inkling
2.1
Rank #30/34 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner44.3
Rank #20/104 · confidence 1 · eval date 2026-02-05
Inkling
40.7
Rank #29/104 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner86.9
Rank #22/95 · confidence 1 · eval date 2026-02-05
Inkling
63.1
Rank #59/95 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner78.5
Rank #18/61 · confidence 1 · eval date 2026-02-05
Inkling
73.5
Rank #36/61 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner77.3
Rank #11/50 · confidence 1 · eval date 2026-02-05
Inkling
63.8
Rank #26/50 · confidence 3 · eval date 2026-07-15
GPT-5.3 Codex
winner64.3
Rank #27/59 · confidence 1 · eval date 2026-02-05
Inkling
57.4
Rank #33/59 · confidence 3 · eval date 2026-07-15
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GPT-5.3 Codex | Inkling |
|---|---|---|
| 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 | Inkling |
|---|---|---|
0 tests | GPT-5.3 Codex gpt-5.3-codex-openai-compact speed / latency N/A / N/A input / output $1.40/M/$11.20/M | Inkling inkling speed / latency N/A / N/A input / output $60.00/M/$60.00/M |
0 tests | GPT-5.3 Codex speed / latency N/A / N/A input / output No data | Inkling 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 | Inkling 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 | Inkling 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 | Inkling speed / latency N/A / N/A input / output No data |
Weighted outcome: GPT-5.3 Codex. 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 inputAudio inputText outputTool callingReasoning |
|---|
