GPT-5.2
- Context
- 400K
- 128K max output
- Input price
- $1.75
- per 1M tokens · OpenAI API
- Output price
- $14.00
- per 1M tokens
- Epoch Capabilities Index
- 153.5
- #34 of 71 listed
- LMArena Text
- 1,437
- #54 of 79 listed
Where to run it
3 offerings · prices as listed| Meter | Tier | Price |
|---|---|---|
| Input | Standard | $1.75 / 1M tokens |
| Batch | $0.88 / 1M tokens | |
| Flex tier | $0.88 / 1M tokens | |
| Fast tier | $3.50 / 1M tokens | |
| Output | Standard | $14.00 / 1M tokens |
| Batch | $7.00 / 1M tokens | |
| Flex tier | $7.00 / 1M tokens | |
| Fast tier | $28.00 / 1M tokens | |
| Cache read | Standard | $0.18 / 1M tokens |
| Batch | $0.088 / 1M tokens | |
| Flex tier | $0.088 / 1M tokens | |
| Fast tier | $0.35 / 1M tokens | |
| Input | Standard | $1.75 / 1M tokens |
| Priority tier | $3.50 / 1M tokens | |
| Output | Standard | $14.00 / 1M tokens |
| Priority tier | $28.00 / 1M tokens | |
| Cache read | Standard | $0.18 / 1M tokens |
| Priority tier | $0.35 / 1M tokens | |
| Input | Standard | $1.93 / 1M tokens |
| Priority tier | $3.85 / 1M tokens | |
| Output | Standard | $15.40 / 1M tokens |
| Priority tier | $30.80 / 1M tokens | |
| Cache read | Standard | $0.20 / 1M tokens |
| Priority tier | $0.39 / 1M tokens | |
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 153.5
#34 of 71 listed models · CI 151.7–155.2
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- LMArena Text 1,437
#54 of 79 listed models · high effort · CI 1,434–1,441 · 49,570 votes
Also listed: gpt-5.2 1,436
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- Epoch AI · FrontierMath Tiers 1–3 67.4%
#21 of 56 listed models · xhigh effort · ±2.8
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- Epoch AI · GPQA Diamond 91.4%
#19 of 64 listed models · xhigh effort · ±1.8
Also listed: high effort 88.2% · medium effort 87.9% · low effort 82.7% · reasoning off 73.2%
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- Epoch AI · SWE-bench Verified 73.8%
#16 of 23 listed models · high effort · ±2
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- LMArena Text · Chinese 1,465
#57 of 79 listed models · high effort · CI 1,455–1,475 · 3,568 votes
Also listed: gpt-5.2 1,464
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Text · Coding 1,489
#49 of 79 listed models · high effort · CI 1,483–1,495 · 12,230 votes
Also listed: gpt-5.2 1,482
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Vision 1,247
#35 of 49 listed models · high effort · CI 1,240–1,253 · 17,926 votes
Also listed: gpt-5.2 1,229
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made