OpenAI, proprietary

# GPT-5.2

> GPT-5.2 by OpenAI, released December 2025. Ranked #34 of 354 with a Noometry Index of 54.1. API: $1.75 in / $14 out per M tokens. 400K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/gpt-5-2
- Last updated: 2026-10-10
- Title: GPT-5.2 Benchmarks, Price & Rank (October 2026) | Noometry

GPT-5.2 by OpenAI ranks 34th of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.1. Its strongest category is multimodal, where it ranks 7th. API pricing starts at $1.75 per million input tokens and $14 per million output tokens, with a 400K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #34 of 354
- **Index score:** 54.1
- **Evidence:** Confirmed 67 results
- **Provider:** [OpenAI](https://noometry.com/providers/openai)
- **Released:** December 11, 2025
- **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:** 15 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** #179 of 219
- **Knowledge cutoff:** August 2025
- **Input:** text, image

## Category scores

Each category score combines every public result we have in that category.

GPT-5.2 category scores

1.  Coding 51.6
2.  Agentic & Tool Use 40.2
3.  Reasoning 50.2
4.  Math 60.0
5.  Knowledge 59.3
6.  Multimodal 51.3
7.  Multilingual 53.4
8.  Instruction Following 74.7
9.  Long Context 44.0
10.  Writing & Preference 66.8
11.  304050607080

GPT-5.2 category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 51.6 | #37 | 7 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 40.2 | #24 | 9 |
| [Reasoning](https://noometry.com/best/reasoning) | 50.2 | #35 | 12 |
| [Math](https://noometry.com/best/math) | 60.0 | #38 | 6 |
| [Knowledge](https://noometry.com/best/knowledge) | 59.3 | #32 | 5 |
| [Multimodal](https://noometry.com/best/multimodal) | 51.3 | #7 | 3 |
| [Multilingual](https://noometry.com/best/multilingual) | 53.4 | #67 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 74.7 | #89 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 44.0 | #78 | 2 |
| [Writing & Preference](https://noometry.com/best/writing) | 66.8 | #32 | 4 |

## Strengths and weaknesses

Categories where GPT-5.2 places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

GPT-5.2: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Multimodal](https://noometry.com/best/multimodal) | 51.3 | +12.7 | #7 of 128, top 6% |
| [Reasoning](https://noometry.com/best/reasoning) | 50.2 | +26.6 | #35 of 350, top 10% |
| [Knowledge](https://noometry.com/best/knowledge) | 59.3 | +21.9 | #32 of 314, top 11% |

### Weakest categories

GPT-5.2: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Instruction Following](https://noometry.com/best/instruction-following) | 74.7 | +3.4 | #89 of 305, top 30% |
| [Long Context](https://noometry.com/best/long-context) | 44.0 | +3.1 | #78 of 296, top 27% |
| [Multilingual](https://noometry.com/best/multilingual) | 53.4 | +6.0 | #67 of 297, top 23% |

## Closest competitors

The models ranked just above and below GPT-5.2. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to GPT-5.2
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [GPT-5.6 Luna](https://noometry.com/models/gpt-5-6-luna) | #30 | 54.6 | $0.45 | 12 | [Compare](https://noometry.com/compare/gpt-5-2-vs-gpt-5-6-luna) |
| [DeepSeek V4 Pro](https://noometry.com/models/deepseek-v4-pro) | #31 | 54.3 | $0.99 | 16 | [Compare](https://noometry.com/compare/deepseek-v4-pro-vs-gpt-5-2) |
| [Gemini 3.5 Flash](https://noometry.com/models/gemini-3-5-flash) | #32 | 54.2 | $3.38 | — | [Compare](https://noometry.com/compare/gemini-3-5-flash-vs-gpt-5-2) |
| [Gemini 3.6 Flash](https://noometry.com/models/gemini-3-6-flash) | #33 | 54.1 | $1.50 | — | [Compare](https://noometry.com/compare/gemini-3-6-flash-vs-gpt-5-2) |
| [DeepSeek V4 Flash](https://noometry.com/models/deepseek-v4-flash) | #35 | 53.6 | $0.26 | 6 | [Compare](https://noometry.com/compare/deepseek-v4-flash-vs-gpt-5-2) |
| [GPT-6 Luna](https://noometry.com/models/gpt-6-luna) | #36 | 53.3 | $0.20 | — | [Compare](https://noometry.com/compare/gpt-5-2-vs-gpt-6-luna) |
| [Grok 4.7](https://noometry.com/models/grok-4-7) | #37 | 53.1 | $3 | — | [Compare](https://noometry.com/compare/gpt-5-2-vs-grok-4-7) |
| [DeepSeek V4.1 Flash](https://noometry.com/models/deepseek-v4-1-flash) | #38 | 52.8 | $0.26 | — | [Compare](https://noometry.com/compare/deepseek-v4-1-flash-vs-gpt-5-2) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## 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

GPT-5.2 Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [SWE-bench Verified](https://noometry.com/benchmarks/swe-bench-verified) | 73.8% | #17 of 32, top 54% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-02-12 |
| [SWE-bench Verified (bash only)](https://noometry.com/benchmarks/swe-bench-bash-only) | 72.8% | #7 of 39, top 18% | high | [SWE-bench](https://www.swebench.com/) | 2026-02-17 |
| [SWE-bench Verified (bash only)](https://noometry.com/benchmarks/swe-bench-bash-only) | 71.8% |  | high | [SWE-bench](https://www.swebench.com/) | 2025-12-11 |
| [LMArena WebDev](https://noometry.com/benchmarks/arena-webdev) | 1416 | #66 of 113, top 59% |  | [LMArena](https://lmarena.ai/leaderboard/webdev) | 2026-10-08 |
| [SWE-bench Multilingual](https://noometry.com/benchmarks/swe-bench-multilingual) | 66.7% | #9 of 13, top 70% | high | [SWE-bench](https://www.swebench.com/) | 2026-02-13 |
| [GSO](https://noometry.com/benchmarks/gso-bench) | 27.4% | #11 of 31, top 36% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 49.6% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 63.4% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 49.6% |  | none | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 72.2% | #16 of 119, top 14% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1447 | #90 of 294, top 31% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1442 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [ALE-Bench](https://noometry.com/benchmarks/ale-bench) | 1,294 | #27 of 105, top 26% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ALE-Bench](https://noometry.com/benchmarks/ale-bench) | 1,250 |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [AlgoTune](https://noometry.com/benchmarks/algotune) | 2.05 | Best of 18 | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Agentic & Tool Use

GPT-5.2 Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Terminal-Bench](https://noometry.com/benchmarks/terminal-bench) | 64.9% | #9 of 41, top 22% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Terminal-Bench](https://noometry.com/benchmarks/terminal-bench) | 64.9% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Berkeley Function Calling Leaderboard](https://noometry.com/benchmarks/bfcl) | 55.9% | #13 of 49, top 27% | fc | [Berkeley Function Calling Leaderboard](https://gorilla.cs.berkeley.edu/leaderboard.html) |  |
| [GDPval](https://noometry.com/benchmarks/gdpval) | 49.7% | Best of 11 | none | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Remote Labor Index](https://noometry.com/benchmarks/remote-labor-index) | 2.1% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Remote Labor Index](https://noometry.com/benchmarks/remote-labor-index) | 2.5% | #10 of 14, top 72% | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [τ²-bench Airline](https://noometry.com/benchmarks/tau2-airline) | 83% | #2 of 7, top 29% | high | [τ²-bench](https://taubench.com/) | 2026-02-26 |
| [τ²-bench Banking](https://noometry.com/benchmarks/tau2-banking) | 32.2% | #13 of 26, top 50% | high | [τ²-bench](https://taubench.com/) | 2026-02-26 |
| [τ²-bench Retail](https://noometry.com/benchmarks/tau2-retail) | 81.6% | #2 of 7, top 29% | high | [τ²-bench](https://taubench.com/) | 2026-02-26 |
| [τ²-bench Telecom](https://noometry.com/benchmarks/tau2-telecom) | 89.7% | #5 of 7, top 72% | high | [τ²-bench](https://taubench.com/) | 2026-02-26 |
| [DeepResearch Bench](https://noometry.com/benchmarks/deepresearch-bench) | 41.1% | #20 of 24, top 84% | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Search](https://noometry.com/benchmarks/arena-search) | 1172 |  |  | [LMArena](https://lmarena.ai/leaderboard/search) | 2026-08-24 |
| [LMArena Search](https://noometry.com/benchmarks/arena-search) | 1207 | #11 of 32, top 35% |  | [LMArena](https://lmarena.ai/leaderboard/search) | 2026-08-24 |
| [METR Time Horizons](https://noometry.com/benchmarks/metr-time-horizons) | 75.3% | #4 of 32, top 13% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Vending-Bench 2](https://noometry.com/benchmarks/vending-bench-2) | 3,591 | #40 of 60, top 67% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

GPT-5.2 Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 0.8% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 43.3% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 9.7% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 26.7% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 52.9% | #33 of 83, top 40% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SimpleBench](https://noometry.com/benchmarks/simplebench) | 45.8% | #47 of 77, top 62% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SimpleBench](https://noometry.com/benchmarks/simplebench) | 45.8% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 73.3% | #17 of 99, top 18% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [NYT Connections (extended)](https://noometry.com/benchmarks/nyt-connections) | 83.6% | #31 of 91, top 35% | xhigh reasoning | [Lech Mazur benchmarks](https://github.com/lechmazur/nyt-connections) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 12.3% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 78.7% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 55.7% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 72.7% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 12.3% |  | none | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 86.2% | #35 of 83, top 43% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 40% |  | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 23% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 40% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 4% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-13 |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 49% | #11 of 129, top 9% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-15 |
| [EnigmaEval](https://noometry.com/benchmarks/enigmaeval) | 10.4% | #14 of 38, top 37% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [EBR-Bench](https://noometry.com/benchmarks/ebr-bench) | 23% | #13 of 24, top 55% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-26 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1445 | #72 of 297, top 25% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1428 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 23% | #36 of 74, top 49% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-06 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 10% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 22% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-28 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 14% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 90.9% | #33 of 151, top 22% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 43.9% | #38 of 125, top 31% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 153.45 | #41 of 213, top 20% |  | [Epoch AI](https://epoch.ai/eci) | 2025-12-11 |
| [ForecastBench](https://noometry.com/benchmarks/forecastbench) | 60.1 | #31 of 72, top 44% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Math

GPT-5.2 Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [FrontierMath (Tiers 1-3)](https://noometry.com/benchmarks/frontiermath) | 67.4% | #27 of 81, top 34% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-11 |
| [FrontierMath Tier 4](https://noometry.com/benchmarks/frontiermath-tier-4) | 31.7% | #28 of 63, top 45% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-11 |
| [MathArena Final-Answer Competitions](https://noometry.com/benchmarks/matharena) | 72% | #12 of 29, top 42% | high | [MathArena](https://matharena.ai/) |  |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 96.1% | #29 of 173, top 17% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 78.9% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 93.9% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 62.2% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-13 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 96.1% |  | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-13 |
| [ProofBench](https://noometry.com/benchmarks/proofbench) | 15% | #58 of 77, top 76% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1435 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1440 | #72 of 285, top 26% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [FrontierMath (Feb 2025 set)](https://noometry.com/benchmarks/frontiermath-2025-02) | 40.3% |  | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [FrontierMath (Feb 2025 set)](https://noometry.com/benchmarks/frontiermath-2025-02) | 26.6% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [FrontierMath (Feb 2025 set)](https://noometry.com/benchmarks/frontiermath-2025-02) | 36.9% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [FrontierMath (Feb 2025 set)](https://noometry.com/benchmarks/frontiermath-2025-02) | 40.7% | #8 of 68, top 12% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-13 |
| [FrontierMath Tier 4 (v1)](https://noometry.com/benchmarks/frontiermath-tier-4-v1) | 18.8% | #10 of 55, top 19% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [FrontierMath Tier 4 (v1)](https://noometry.com/benchmarks/frontiermath-tier-4-v1) | 6.3% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [FrontierMath Tier 4 (v1)](https://noometry.com/benchmarks/frontiermath-tier-4-v1) | 16.7% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [FrontierMath Tier 4 (v1)](https://noometry.com/benchmarks/frontiermath-tier-4-v1) | 18.8% |  | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-14 |

### Knowledge

GPT-5.2 Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 88.2% |  | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 82.7% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 87.9% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 73.2% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-13 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 91.4% | #26 of 186, top 14% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-13 |
| [Humanity's Last Exam](https://noometry.com/benchmarks/hle) | 27.8% | #12 of 41, top 30% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified) | 34.3% |  | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified) | 32.8% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified) | 32.7% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified) | 37.1% | #45 of 77, top 59% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) (lower is better) | 10.8% |  |  | [Vectara Hallucination Leaderboard](https://github.com/vectara/hallucination-leaderboard) |  |
| [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) (lower is better) | 8.4% | #39 of 96, top 41% |  | [Vectara Hallucination Leaderboard](https://github.com/vectara/hallucination-leaderboard) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1438 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1445 | #74 of 273, top 28% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multimodal

GPT-5.2 Multimodal benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Vision](https://noometry.com/benchmarks/arena-vision) | 1268 | #39 of 122, top 32% |  | [LMArena](https://lmarena.ai/leaderboard/vision) | 2026-10-09 |
| [LMArena Vision](https://noometry.com/benchmarks/arena-vision) | 1246 |  | high | [LMArena](https://lmarena.ai/leaderboard/vision) | 2026-10-09 |
| [VPCT](https://noometry.com/benchmarks/vpct) | 67% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [VPCT](https://noometry.com/benchmarks/vpct) | 84% | #2 of 24, top 9% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Furniture Assembly](https://noometry.com/benchmarks/furniture-assembly) | 38.3% | #16 of 31, top 52% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2026-09-10 |
| [LMArena Document](https://noometry.com/benchmarks/arena-document) | 1405 | #36 of 38, top 95% | high | [LMArena](https://lmarena.ai/leaderboard/document) | 2026-09-13 |

### Multilingual

GPT-5.2 Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1425 | #67 of 297, top 23% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1405 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1460 | #91 of 285, top 32% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1447 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1438 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1455 | #61 of 223, top 28% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1448 | #46 of 231, top 20% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1444 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1418 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1420 | #41 of 211, top 20% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1392 | #66 of 213, top 31% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1374 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1415 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1440 | #52 of 283, top 19% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1433 | #78 of 226, top 35% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1413 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

GPT-5.2 Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1417 | #78 of 298, top 27% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1409 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

GPT-5.2 Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [CL-bench](https://noometry.com/benchmarks/cl-bench) | 18.2% | #11 of 19, top 58% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CL-bench](https://noometry.com/benchmarks/cl-bench) | 18.1% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1428 | #80 of 291, top 28% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1413 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

GPT-5.2 Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1439 | #65 of 297, top 22% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1416 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1401 | #77 of 295, top 27% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1376 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 1703 | #30 of 115, top 27% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1458 | #40 of 295, top 14% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1419 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

GPT-5.2 API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [azure](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) | $1.75 | $14 | $0.13 | 2026-10-10 |
| [openai](https://platform.openai.com/docs/models) | $1.75 | $14 | $0.17 | 2026-10-10 |
| [openrouter](https://openrouter.ai/openai/gpt-5.2) | $1.75 | $14 | $0.17 | 2026-10-10 |

[All OpenAI API prices →](https://noometry.com/llm-pricing/openai) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare GPT-5.2

-   [GPT-5.2 vs GPT-5.1](https://noometry.com/compare/gpt-5-1-vs-gpt-5-2)
-   [GPT-5.2 vs Gemini 3.6 Flash](https://noometry.com/compare/gemini-3-6-flash-vs-gpt-5-2)
-   [GPT-5.2 vs DeepSeek V4 Flash](https://noometry.com/compare/deepseek-v4-flash-vs-gpt-5-2)
-   [GPT-5.2 vs Gemini 3.5 Flash](https://noometry.com/compare/gemini-3-5-flash-vs-gpt-5-2)
-   [GPT-5.2 vs GPT-6 Luna](https://noometry.com/compare/gpt-5-2-vs-gpt-6-luna)
-   [GPT-5.2 vs DeepSeek V4 Pro](https://noometry.com/compare/deepseek-v4-pro-vs-gpt-5-2)
-   [GPT-5.2 vs Grok 4.7](https://noometry.com/compare/gpt-5-2-vs-grok-4-7)
-   [GPT-5.2 vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-gpt-5-2)
-   [GPT-5.2 vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-gpt-5-2)
-   [GPT-5.2 vs Kimi K3](https://noometry.com/compare/gpt-5-2-vs-kimi-k3)
-   [GPT-5.2 vs Grok 4.6](https://noometry.com/compare/gpt-5-2-vs-grok-4-6)
-   [GPT-5.2 vs Qwen3.8 Max](https://noometry.com/compare/gpt-5-2-vs-qwen3-8-max)
-   [GPT-5.2 vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-gpt-5-2)
-   [GPT-5.2 vs Muse Spark 1.3](https://noometry.com/compare/gpt-5-2-vs-muse-spark-1-3)

## Other OpenAI models

-   [GPT-6 Astra](https://noometry.com/models/gpt-6-astra)70.8
-   [GPT-6.1 Sol](https://noometry.com/models/gpt-6-1-sol)65.6
-   [GPT-5.6 Sol](https://noometry.com/models/gpt-5-6-sol)65.0
-   [GPT-5.5 Pro](https://noometry.com/models/gpt-5-5-pro)64.3
-   [GPT-5.5](https://noometry.com/models/gpt-5-5)63.4
-   [GPT-6 Sol](https://noometry.com/models/gpt-6-sol)61.8
-   [GPT-5.4](https://noometry.com/models/gpt-5-4)59.4
-   [GPT-5.6 Terra](https://noometry.com/models/gpt-5-6-terra)59.2

## Frequently asked questions

### How good is GPT-5.2?

GPT-5.2 by OpenAI ranks 34th of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.1. Its strongest category is multimodal, where it ranks 7th. 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-5.2 cost?

GPT-5.2 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-5.2's context window?

GPT-5.2 accepts up to 400K tokens of input and can write up to 128K tokens in one response.

### Is GPT-5.2 open source?

No. GPT-5.2 is proprietary and available only through OpenAI's API and partner platforms.

### How fast is GPT-5.2?

GPT-5.2 generated about 15 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are GPT-5.2's strengths and weaknesses?

Relative to other ranked models, GPT-5.2 places best in multimodal, reasoning, knowledge and lowest in instruction following, long context, multilingual.

### What is GPT-5.2 best at?

Its best category is multimodal, where it ranks 7th on Noometry.

### Cite this page

Noometry. (2026). GPT-5.2 benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/gpt-5-2

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/gpt-5-2.md).