OpenAIGPT-5.3 Chat
GPT-5.3 Chat is an OpenAI proprietary model, released 3 Mar 2026. It is not yet ranked: 4 independent results so far, and the index needs at least five across two categories. At $4.81 per million tokens blended it is among the most expensive ranked models. It has been measured at 2 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 22 Oct 2026.
- Blended price
- $4.81/M
- $1.75 in · $14.00 out
- Output speed
- –
- First answer
- –
- Context
- 128k
- Full answer
- –
- Cost per run
- –
- Released
- 3 Mar 2026
- Reasoning64
- Coding63
- Maths61
- Human preference64
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| xhigh | – | – | – | – | $0.0049 | |
| not statedbest | – | – | – | – | $0.0049 | Coding 63 · Human preference 64 · Maths 61 · Reasoning 64 |
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Hard Prompts | 1473#80 | Arena (LMArena) |
Coding
| Benchmark | xhigh | not stated | Source | Trend |
|---|---|---|---|---|
| Arena Codingeffort not stated | – | 1497#85 | Arena (LMArena) | |
| SWE Atlas: Codebase QnAnot in index | 32.6%#14 | – | Scale AI SEAL | |
| SWE Atlas: Refactoringnot in index | 42.4%#9 | – | Scale AI SEAL | |
| SWE Atlas: Test Writingnot in index | 39.0%#12 | – | Scale AI SEAL |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Maths | 1431#104 | Arena (LMArena) |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Instruction Followingnot in index | 1436#85 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1450#75 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1407#96 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1467#67 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1456#79 | Arena (LMArena) |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0049 | – | – |
| Summarize a 30-page report | 12,000 / 600 | $0.029 | – | – |
| Code edit | 6,000 / 1,500 | $0.032 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.161 | – | – |
| Structured extraction | 2,000 / 200 | $0.0063 | – | – |
More from OpenAI
See also
Questions people ask
- Why does GPT-5.3 Chat have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories; as of 24 Oct 2026 GPT-5.3 Chat has 4 that count. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- How much does GPT-5.3 Chat cost per 1M tokens?
- As of 24 Oct 2026, GPT-5.3 Chat costs $1.75 per 1M input tokens and $14.00 per 1M output tokens, $4.81 blended (three input tokens per output token).
- When was GPT-5.3 Chat released?
- OpenAI released GPT-5.3 Chat on 3 Mar 2026. BenchLeader has results for it at 2 reasoning-effort settings.
Data as of 24 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “GPT-5.3 Chat: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/gpt-5-3.