gpt-5.2-2025-12-11-high: benchmark scores, price and ranking
gpt-5.2-2025-12-11-high from OpenAI ranks #80 of 743 LLMs on the LLMs Tiger aggregate benchmark score (52.1), based on 7 benchmark results captured up to 2026-10-13.
- Organisation
- OpenAI
- Type
- Frontier model
- Open weights
- No
- Released
- 2025-12-11 (source: name)
- Cheapest API price
- $1.75 in / $14.00 out per million tokens (via azure, observed 2026-10-13T20:47Z)
- Aggregate rank
- #80 of 743 (score 52.1)
Relative to other models, gpt-5.2-2025-12-11-high is strongest on LiveBench Agentic Coding (#4 of 17) and weakest on LiveBench IF (#12 of 17).
Across the 7 benchmarks where at least ten models are scored, gpt-5.2-2025-12-11-high is in the top 10% on 0 and in the top half on 5.
Its cheapest listed input price, $1.75 per million tokens, is lower than that of 24% of the 427 models with a listed price.
gpt-5.2-2025-12-11-high benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| LiveBench Agentic Coding | 50.3% | #4 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Mathematics | 93.2% | #4 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Data Analysis | 78.2% | #6 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Reasoning | 83.2% | #6 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Language | 79.8% | #7 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Coding | 76.1% | #10 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench IF | 61.8% | #12 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
About gpt-5.2-2025-12-11-high
gpt-5.2-2025-12-11-high is a frontier model from OpenAI. It was released on 2025-12-11, according to the model's own name. The cheapest API listing we track charges $1.75 per million input tokens and $14.00 per million output tokens, through azure. We hold 7 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where gpt-5.2-2025-12-11-high stands
On our aggregate score, gpt-5.2-2025-12-11-high is #80 of 743 ranked models, in the top quarter. Its score is 52.1; the scale is centred on 50, so it sits 2.1 points above the typical model. That beats 89% of the ranked field. Among the 88 ranked OpenAI models it is #13. The next one up is GPT-5.2 Codex at 52.2. The next one down is GPT-5.2 (xhigh) at 51.9.
gpt-5.2-2025-12-11-high, benchmark by benchmark
LiveBench Agentic Coding puts gpt-5.2-2025-12-11-high at 50.3%, #4 of 17. That beats 76% of the models tested, but 5.8 points short of claude-opus-4-8-xhigh-effort (56.1%). The results either side are GPT-5.5 (xhigh) (52.1%) and GPT-5.2 Codex (49.4%). It covers LiveBench release 2026_06_25. The board median is 45.8%, so gpt-5.2-2025-12-11-high is 4.4 points above it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
On LiveBench Mathematics, gpt-5.2-2025-12-11-high reaches 93.2%. It ranks #4 of 17, ahead of 76% of the field, and 2.7 points behind GPT-5.5 (xhigh) at 95.9%. The results either side are GPT-5.4 (xhigh) (94.1%) and gemini-3.1-pro-preview-high (91.0%). It covers LiveBench release 2026_06_25. The board median is 88.2%, so gpt-5.2-2025-12-11-high is 4.9 points above it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
gpt-5.2-2025-12-11-high manages 78.2% on LiveBench Data Analysis, good for #6 of 17. GPT-5.5 (xhigh) leads at 81.6%, 3.4 points further up, and 65% of models sit below. The results either side are GPT-5.2 Codex (78.2%) and MiniMax-M3 (76.2%). It covers LiveBench release 2026_06_25. The board median is 71.8%, so gpt-5.2-2025-12-11-high is 6.4 points above it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
LiveBench Reasoning puts gpt-5.2-2025-12-11-high at 83.2%, #6 of 17. That beats 65% of the models tested, but 6.5 points short of claude-opus-4-8-xhigh-effort (89.7%). The results either side are Qwen3.7 Max (83.3%) and Kimi K2.7 Code (82.8%). It covers LiveBench release 2026_06_25. The board median is 81.1%, so gpt-5.2-2025-12-11-high is 2.1 points above it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
On LiveBench Language, gpt-5.2-2025-12-11-high reaches 79.8%. It ranks #7 of 17, ahead of 59% of the field, and 7.6 points behind GPT-5.5 (xhigh) at 87.4%. The results either side are claude-opus-4-5-20251101-thinking-64k-high-effort (81.3%) and Qwen3.7 Max (79.7%). It covers LiveBench release 2026_06_25. The board median is 77.9%, so gpt-5.2-2025-12-11-high is 1.9 points above it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
gpt-5.2-2025-12-11-high lands below the middle on LiveBench Coding: 76.1%, #10 of 17, with 53% of the field scoring higher. GPT-5.2 Codex leads at 83.6%; the closest result above is gemini-3.1-pro-preview-high at 76.5%. It covers LiveBench release 2026_06_25. The board median is 76.5%, so gpt-5.2-2025-12-11-high is 0.4 points below it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
gpt-5.2-2025-12-11-high lands below the middle on LiveBench IF: 61.8%, #12 of 17, with 65% of the field scoring higher. gemini-3.1-pro-preview-high leads at 79.1%; the closest result above is claude-opus-4-5-20251101-thinking-64k-high-effort at 62.5%. It covers LiveBench release 2026_06_25. The board median is 65.2%, so gpt-5.2-2025-12-11-high is 3.4 points below it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
Strengths and weaknesses
Software engineering: solid, ahead of 59% of the field on average across 2 benchmarks. Its best board here is LiveBench Agentic Coding (#4 of 17) and its weakest is LiveBench Coding (#10 of 17). Reasoning, maths and science: solid, ahead of 71% of the field on average across 2 benchmarks. Its best board here is LiveBench Mathematics (#4 of 17) and its weakest is LiveBench Reasoning (#6 of 17). General knowledge and chat: solid, ahead of 51% of the field on average across 3 benchmarks. Its best board here is LiveBench Data Analysis (#6 of 17) and its weakest is LiveBench IF (#12 of 17).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so gpt-5.2-2025-12-11-high costs more than the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4 Flash 0731 (max) ($0.016, 53.1), GLM-5.2 (high) ($0.060, 51.6), Qwen3-Coder-30B-A3B-Instruct ($0.070, 52.7). Similar scores cost more on Grok 4.6 (xhigh) ($2.00) and Grok 4.7 (xhigh) ($2.00).
Release history
The OpenAI model released before it was GPT-5.1-Codex-Max on 2025-11-19, which scores 50.2. The next one was GPT-5.2 (xhigh) on 2025-12-11, at 51.9.
Reading these numbers
The 7 scores on this page come from 1 source: LiveBench 2026_06_25 official CSV (7). 7 of them come from an official leaderboard and 0 from datasets or third-party runs. With 7 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #77 Ornith-1.5-397B (52.2)
- #78 Claude Code + Opus 5 (52.1)
- #79 Qwen3.8-2.4T-A95B (52.1)
- #81 EXAONE-4.5-33B (52.1)
- #82 Claude Haiku 5.5 (max) (52.1)
- #83 NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (52.0)
More from OpenAI
- GPT-6 Astra (max) (#2, 64.0)
- GPT-6.1 Sol (max) (#5, 60.6)
- GPT-5.6 Sol (max) (#6, 60.1)
- GPT-6 Sol (max) (#7, 60.0)
- GPT-5.5 (xhigh) (#11, 58.0)
- GPT-5.6 Terra (max) (#12, 57.8)
Compare it on the live leaderboard → · How the aggregate score works