Leaderboard
Language ModelsProprietary
Gemini 2.5 Pro
Prior-generation Gemini flagship; widely used, slated for deprecation.
Crosshair Index
54.1
#26 of 32 · Language Models
- Provider
- Google DeepMind
- Released
- 2025-06-05
- Parameters
- Undisclosed
- Context
- 1.048576M tokens
Token pricing
- Input
- $1.25 /1M
- Output
- $10 /1M
- Cache read
- $0.125 /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
74
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 | 86.4% | Google DeepMind — Gemini 2.5 Pro model cardvendor | unverified |
| Humanity's Last Exam Frontier | 21.6% | Google DeepMind — Gemini 2.5 Pro model cardvendor | unverified |
| SWE-bench Verified Agentic Coding | 59.6% | Google DeepMind — Gemini 2.5 Pro model cardvendor | unverified |
| LiveCodeBench Coding | 69% | Google DeepMind — Gemini 2.5 Pro model cardvendor | unverified |
| MMLU-Pro Knowledge | — | not evaluated | |
| LMArena Elo Human Preference | 1,446 | LMArena (arena.ai)3rd-party | unverified |
| AA Intelligence Index Composite | 35 | Artificial Analysis3rd-party | unverified |
| Corporate Finance Finance | 60.8% | Vals AI — CorpFin v23rd-party | unverified |
| LegalBench Law | — | not evaluated | |
| TaxEval Tax & Accounting | — | not evaluated | |
| Medical Coding Medicine | 50.6% | Vals AI — MedCode3rd-party | unverified |