OpenAI, proprietary
GPT-5-Codex
GPT-5-Codex by OpenAI ranks 192nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 37.9. Its strongest category is agentic & tool use, where it ranks 72nd. API pricing starts at $1.25 per million input tokens and $10 per million output tokens, with a 400K-token context window.
Last verified
Specifications
- Noometry rank
- #192 of 354
- Index score
- 37.9
- Evidence
- Reported 3 results
- Provider
- OpenAI
- Released
- September 15, 2025
- Weights
- Proprietary
- Reasoning
- Yes
- Context window
- 400K
- Max output
- 128K
- Input price
- $1.25 / M
- Output price
- $10 / M
- Blended price
- $3.44 / M
- Output speed
- 95 tokens/s Kagi
- Value
- #180 of 219
- Knowledge cutoff
- September 2024
- Input
- text, image
Category scores
Each category score combines every public result we have in that category.
- Coding 42.4
- Agentic & Tool Use 31.0
- Reasoning 30.9
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 42.4 | #103 | 1 |
| Agentic & Tool Use | 31.0 | #72 | 1 |
| Reasoning | 30.9 | #83 | 1 |
Strengths and weaknesses
Categories where GPT-5-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 |
|---|---|---|---|
| Reasoning | 30.9 | +7.3 | #83 of 350, top 24% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Agentic & Tool Use | 31.0 | +0.7 | #72 of 154, top 47% |
Closest competitors
The models ranked just above and below GPT-5-Codex. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| MiniMax-M2.5 | #188 | 38.3 | $0.52 | 49 | Compare |
| Nova Premier 1.0 | #189 | 38.3 | $5 | 9 | Compare |
| Qwen3-Coder 480B-A35B Instruct | #190 | 38.1 | $3 | 67 | Compare |
| Olmo 3.1 32b Think | #191 | 37.9 | — | — | Compare |
| Hunyuan Standard 2025 02 10 | #193 | 37.9 | — | — | Compare |
| Gemini 2.0 Flash-Lite | #194 | 37.8 | — | — | Compare |
| DeepSeek-R1-Distill-Llama-70B | #195 | 37.8 | — | 18 | Compare |
| MiniMax-M2.7 | #196 | 37.7 | $0.52 | — | 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 |
|---|---|---|---|---|---|
| WeirdML | 54.5% | #39 of 119, top 33% | Epoch AI | ||
| WeirdML | 54.5% | high | Epoch AI |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Terminal-Bench | 44.3% | #21 of 41, top 52% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Kagi LLM Benchmark | 70.3% | #23 of 99, top 24% | Kagi LLM Benchmark |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| azure | $1.25 | $10 | $0.13 | 2026-10-10 |
Compare GPT-5-Codex
- GPT-5-Codex vs Olmo 3.1 32b Think
- GPT-5-Codex vs Hunyuan Standard 2025 02 10
- GPT-5-Codex vs Qwen3-Coder 480B-A35B Instruct
- GPT-5-Codex vs Gemini 2.0 Flash-Lite
- GPT-5-Codex vs Nova Premier 1.0
- GPT-5-Codex vs DeepSeek-R1-Distill-Llama-70B
- GPT-5-Codex vs Claude Fable 5.1
- GPT-5-Codex vs Gemini 3.8 Flash
- GPT-5-Codex vs Kimi K3
- GPT-5-Codex vs Grok 4.6
- GPT-5-Codex vs Qwen3.8 Max
- GPT-5-Codex vs GLM-5.3
- GPT-5-Codex vs Muse Spark 1.3
- GPT-5-Codex vs DeepSeek V4 Pro
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-Codex?
GPT-5-Codex by OpenAI ranks 192nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 37.9. Its strongest category is agentic & tool use, where it ranks 72nd. API pricing starts at $1.25 per million input tokens and $10 per million output tokens, with a 400K-token context window.
How much does GPT-5-Codex cost?
GPT-5-Codex costs $1.25 per million input tokens and $10 per million output tokens on azure, with cached input at $0.13.
What is GPT-5-Codex's context window?
GPT-5-Codex accepts up to 400K tokens of input and can write up to 128K tokens in one response.
Is GPT-5-Codex open source?
No. GPT-5-Codex is proprietary and available only through OpenAI's API and partner platforms.
How fast is GPT-5-Codex?
GPT-5-Codex generated about 95 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.
What are GPT-5-Codex's strengths and weaknesses?
Relative to other ranked models, GPT-5-Codex places best in reasoning and lowest in agentic & tool use.
What is GPT-5-Codex best at?
Its best category is agentic & tool use, where it ranks 72nd on Noometry.