Leaderboard
Language ModelsProprietary
GPT-5.5
OpenAI's flagship multimodal reasoning model (figures shown for the high reasoning-effort config).
Crosshair Index
73.0
#6 of 32 · Language Models
- Provider
- OpenAI
- Released
- 2026-04-23
- Parameters
- Undisclosed
- Context
- 400K tokens
Token pricing
- Input
- $5 /1M
- Output
- $30 /1M
- Cache read
- $0.5 /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.
Investment Banking
81
skill
Financial analysis over filings and credit agreements — valuation math, document QA, and the quantitative reasoning behind deals.
Scorecard
| Benchmark | Score | Source | Status |
|---|---|---|---|
| GPQA Diamond Reasoning | 93.6% | OpenAI — GPT-5.5vendor | unverified |
| Humanity's Last Exam Frontier | 41.4% | OpenAI — GPT-5.5vendor | unverified |
| SWE-bench Verified Agentic Coding | — | not evaluated | |
| LiveCodeBench Coding | — | not evaluated | |
| MMLU-Pro Knowledge | — | not evaluated | |
| LMArena Elo Human Preference | 1,474 | LMArena (arena.ai)3rd-party | unverified |
| AA Intelligence Index Composite | 60 | Artificial Analysis3rd-party | unverified |
| Corporate Finance Finance | 68.4% | Vals AI — CorpFin v23rd-party | unverified |
| LegalBench Law | 86.5% | Vals AI — LegalBench3rd-party | unverified |
| TaxEval Tax & Accounting | 75% | Vals AI — TaxEval v23rd-party | unverified |
| Medical Coding Medicine | 49.1% | Vals AI — MedCode3rd-party | unverified |