OpenAI, proprietary
GPT-5.3 Codex
GPT-5.3 Codex by OpenAI ranks 69th of 354 ranked models on the Noometry Index as of October 2026, with a score of 45.8. Its strongest category is agentic & tool use, where it ranks 9th. API pricing starts at $1.75 per million input tokens and $14 per million output tokens, with a 400K-token context window.
Last verified
Specifications
- Noometry rank
- #69 of 354
- Index score
- 45.8
- Evidence
- Reported 8 results
- Provider
- OpenAI
- Released
- February 5, 2026
- Weights
- Proprietary
- Reasoning
- Yes
- Context window
- 400K
- Max output
- 128K
- Input price
- $1.75 / M
- Output price
- $14 / M
- Blended price
- $4.81 / M
- Output speed
- Not measured
- Value
- #186 of 219
- Knowledge cutoff
- August 2025
- Input
- text, image, pdf
Category scores
Each category score combines every public result we have in that category.
- Coding 48.6
- Agentic & Tool Use 48.0
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 48.6 | #56 | 3 |
| Agentic & Tool Use | 48.0 | #9 | 1 |
Strengths and weaknesses
Categories where GPT-5.3 Codex places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Agentic & Tool Use | 48.0 | +17.7 | #9 of 154, top 6% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Coding | 48.6 | +9.9 | #56 of 340, top 17% |
Closest competitors
The models ranked just above and below GPT-5.3 Codex. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Grok 4.20 Multi-Agent | #65 | 46.2 | $1.56 | — | Compare |
| GLM-5 | #66 | 46.1 | $1.55 | 23 | Compare |
| Qwen3.5 397B-A17B | #67 | 46.0 | $1.35 | 9 | Compare |
| Qwen3.8 27B | #68 | 46.0 | $1.11 | — | Compare |
| Kimi K2 Thinking Turbo | #70 | 45.8 | — | — | Compare |
| Qwen3.5 Max Preview | #71 | 45.3 | — | — | Compare |
| Qwen3.7 Plus | #72 | 45.3 | $0.70 | — | Compare |
| Hy4 preview | #73 | 45.3 | $1.13 | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| SWE-bench Verified | 74.8% | #15 of 32, top 47% | high | Epoch AI | 2026-02-25 |
| LMArena WebDev | 1409 | #69 of 113, top 62% | LMArena | 2026-10-08 | |
| WeirdML | 79.3% | #10 of 119, top 9% | Epoch AI | ||
| WeirdML | 77.9% | xhigh | Epoch AI | ||
| ALE-Bench | 1,655 | #12 of 105, top 12% | xhigh | Epoch AI |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Terminal-Bench | 78.4% | #6 of 41, top 15% | Epoch AI | ||
| METR Time Horizons | 74.5% | #6 of 32, top 19% | Epoch AI | ||
| Vending-Bench 2 | 5,940 | #20 of 60, top 34% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Epoch Capabilities Index | 156.77 | #18 of 213, top 9% | Epoch AI | 2026-02-05 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| azure | $1.75 | $14 | $0.17 | 2026-10-10 |
| openai | $1.75 | $14 | $0.17 | 2026-10-10 |
| openrouter | $1.75 | $14 | $0.17 | 2026-10-10 |
Compare GPT-5.3 Codex
- GPT-5.3 Codex vs GPT-5.2 Codex
- GPT-5.3 Codex vs Qwen3.8 27B
- GPT-5.3 Codex vs Kimi K2 Thinking Turbo
- GPT-5.3 Codex vs Qwen3.5 397B-A17B
- GPT-5.3 Codex vs Qwen3.5 Max Preview
- GPT-5.3 Codex vs GLM-5
- GPT-5.3 Codex vs Qwen3.7 Plus
- GPT-5.3 Codex vs Claude Fable 5.1
- GPT-5.3 Codex vs Gemini 3.8 Flash
- GPT-5.3 Codex vs Kimi K3
- GPT-5.3 Codex vs Grok 4.6
- GPT-5.3 Codex vs Qwen3.8 Max
- GPT-5.3 Codex vs GLM-5.3
- GPT-5.3 Codex vs Muse Spark 1.3
Other OpenAI models
- GPT-6 Astra70.8
- GPT-6.1 Sol65.6
- GPT-5.6 Sol65.0
- GPT-5.5 Pro64.3
- GPT-5.563.4
- GPT-6 Sol61.8
- GPT-5.459.4
- GPT-5.6 Terra59.2
Frequently asked questions
How good is GPT-5.3 Codex?
GPT-5.3 Codex by OpenAI ranks 69th of 354 ranked models on the Noometry Index as of October 2026, with a score of 45.8. Its strongest category is agentic & tool use, where it ranks 9th. API pricing starts at $1.75 per million input tokens and $14 per million output tokens, with a 400K-token context window.
How much does GPT-5.3 Codex cost?
GPT-5.3 Codex costs $1.75 per million input tokens and $14 per million output tokens on OpenAI's own API, with cached input at $0.17.
What is GPT-5.3 Codex's context window?
GPT-5.3 Codex accepts up to 400K tokens of input and can write up to 128K tokens in one response.
Is GPT-5.3 Codex open source?
No. GPT-5.3 Codex is proprietary and available only through OpenAI's API and partner platforms.
What are GPT-5.3 Codex's strengths and weaknesses?
Relative to other ranked models, GPT-5.3 Codex places best in agentic & tool use and lowest in coding.
What is GPT-5.3 Codex best at?
Its best category is agentic & tool use, where it ranks 9th on Noometry.