GPT-5.2 (batch)
OpenAI · released Dec 10, 2025
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...
Specification
- Context window
- 400K
- Max output
- 128K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- Yes
Intelligence
43.3
92th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
—
Median across providers
Latency
—
Time to first token
Cost per task
$0.60
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- AIME 202599.0%
- GPQA Diamond90.3%
- LiveCodeBench88.9%
- MMLU-Pro87.4%
- τ²-bench (Telecom)84.8%
- AA-LCR (long context)79.3%
- IFBench75.4%
- SciCode52.1%
- Terminal-Bench Hard47.0%
- Humanity's Last Exam37.7%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| AIME 2025 | 99.0% |
| GPQA Diamond | 90.3% |
| LiveCodeBench | 88.9% |
| MMLU-Pro | 87.4% |
| τ²-bench (Telecom) | 84.8% |
| AA-LCR (long context) | 79.3% |
| IFBench | 75.4% |
| SciCode | 52.1% |
| Terminal-Bench Hard | 47.0% |
| Humanity's Last Exam | 37.7% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Kimi K2.6Moonshot AI45.1
- GPT-5.2 (batch)OpenAI43.3
- GPT-5.2OpenAI43.3
- Kimi K2.7 CodeMoonshot AI43.0
- MiMo-V2.5-ProXiaomi42.9
- InklingThinking Machines42.3
- Hy3Tencent42.2
- Nex-N2-ProNex AGI41.7
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Kimi K2.6 | 45.1 |
| GPT-5.2 (batch) | 43.3 |
| GPT-5.2 | 43.3 |
| Kimi K2.7 Code | 43.0 |
| MiMo-V2.5-Pro | 42.9 |
| Inkling | 42.3 |
| Hy3 | 42.2 |
| Nex-N2-Pro | 41.7 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.875
- Output / 1M tokens
- $7
- Cached input / 1M
- $0.087
- Blended 3:1
- $2.41
One task, estimated
$0.60
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.