Leaderboard
Language ModelsProprietary
GPT-5.2
Prior OpenAI flagship; still available but scheduled for API retirement in Aug 2026.
Crosshair Index
65.3
#21 of 32 · Language Models
- Provider
- OpenAI
- Released
- 2025-12-11
- Parameters
- Undisclosed
- Context
- 400K tokens
Token pricing
- Input
- $1.75 /1M
- Output
- $14 /1M
- Cache read
- $0.175 /1M
USD per 1M tokens · cache read = cached input (hit), cache write = caching surcharge · official list pricing (June 2026).
Industry skill web
Professional-domain strengths, composed from the benchmarks relevant to each field. Highlight an axis to see the benchmarks behind it.
Software Engineering
80
skill
Shipping working code against real repositories: bug fixes, feature patches, and competitive programming under tests.
Scorecard
| Benchmark | Score | Source | Status |
|---|---|---|---|
| GPQA Diamond Reasoning | 92.4% | llm-stats — GPT-5.2 (vendor-reported)3rd-party | unverified |
| Humanity's Last Exam Frontier | 34.5% | llm-stats — GPT-5.2 (vendor-reported)3rd-party | unverified |
| SWE-bench Verified Agentic Coding | 80% | llm-stats — GPT-5.2 (vendor-reported)3rd-party | unverified |
| LiveCodeBench Coding | — | not evaluated | |
| MMLU-Pro Knowledge | — | not evaluated | |
| LMArena Elo Human Preference | 1,435 | LMArena (arena.ai)3rd-party | unverified |
| AA Intelligence Index Composite | 51 | Artificial Analysis3rd-party | unverified |
| Corporate Finance Finance | 65.9% | Vals AI — CorpFin v23rd-party | unverified |
| LegalBench Law | 82.8% | Vals AI — LegalBench3rd-party | unverified |
| TaxEval Tax & Accounting | 75.8% | Vals AI — TaxEval v23rd-party | unverified |
| Medical Coding Medicine | 49.7% | Vals AI — MedCode3rd-party | unverified |