OpenAIGPT-5.2 Pro
GPT-5.2 Pro is an OpenAI proprietary reasoning model, released 11 Dec 2025. It is not yet ranked: 3 independent results so far, and the index needs at least five across two categories. At $57.75 per million tokens blended it is among the most expensive ranked models. It has been measured at 4 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 11 Dec 2025.stale: no new result in six months
- Blended price
- $57.75/M
- $21.00 in · $168.00 out
- Output speed
- –
- First answer
- –
- Context
- 400k
- Full answer
- –
- Cost per run
- –
- Released
- 11 Dec 2025
- Reasoning62
- Maths61
Versions
OpenAI has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| GPT-5.5 Proxhigh | 23 Apr 2026 | 65.3 | #40 |
| GPT-5.4 Pro | 4 Mar 2026 | 63.3 | #68 |
| GPT-5.2 Proxhighthis page | 11 Dec 2025 | – | – |
| GPT-5 Pro | 7 Aug 2025 | 59.8 | #121 |
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 |
|---|---|---|---|---|---|---|
| medium | – | – | – | – | $0.059 | Reasoning 53 |
| high | – | – | – | – | $0.059 | Reasoning 58 |
| xhighbest | – | – | – | – | $0.059 | Maths 61 · Reasoning 62 |
| not stated | – | – | – | – | $0.059 | Knowledge 52 · Reasoning 57 |
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 | medium | high | xhigh | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| SimpleBencheffort not stated | – | – | – | 57.4%#35 | SimpleBench | |
| ARC-AGI-1 | 81.2%#119 | 85.7%#110 | 90.5%#74 | – | ARC Prize | |
| ARC-AGI-2 | 38.5%#120 | 54.2%#102 | – | – | ARC Prize | |
| Chess Puzzlesnot in index | – | – | 60.0%#9 | – | Epoch AI Benchmarking Hub |
Maths
| Benchmark | xhigh | Source | Trend |
|---|---|---|---|
| FrontierMath Tiers 1–3 | 74.0%#24 | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | 46.0%#31 | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| PRBench Finance | 46.3%#18 | Scale AI SEAL | |
| PRBench Legal | 45.4%#21 | Scale AI SEAL |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 156.3#30 | Epoch AI Benchmarking Hub |
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 | $0.059 | – | – |
| Summarize a 30-page report | 12,000 / 600 | $0.353 | – | – |
| Code edit | 6,000 / 1,500 | $0.378 | – | – |
| Agentic coding session | 60,000 / 4,000 | $1.93 | – | – |
| Structured extraction | 2,000 / 200 | $0.076 | – | – |
More from OpenAI
See also
Questions people ask
- Why does GPT-5.2 Pro have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories; as of 24 Oct 2026 GPT-5.2 Pro has 3 that count. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- How much does GPT-5.2 Pro cost per 1M tokens?
- As of 24 Oct 2026, GPT-5.2 Pro costs $21.00 per 1M input tokens and $168.00 per 1M output tokens, $57.75 blended (three input tokens per output token).
- When was GPT-5.2 Pro released?
- OpenAI released GPT-5.2 Pro on 11 Dec 2025. BenchLeader has results for it at 4 reasoning-effort settings.
Data as of 24 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “GPT-5.2 Pro: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/gpt-5-2-pro.