Leaderboard
Language ModelsProprietary
Gemini 3 Pro
Google DeepMind's frontier multimodal, long-context model.
Crosshair Index
71.1
#8 of 32 · Language Models
- Provider
- Google DeepMind
- Released
- 2025-11-18
- Parameters
- Undisclosed
- Context
- 1M tokens
Token pricing
- Input
- $2 /1M
- Output
- $12 /1M
- Cache read
- $0.2 /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
78
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 | 91.9% | Google — Gemini 3 Provendor | unverified |
| Humanity's Last Exam Frontier | 37.5% | Google — Gemini 3 Provendor | unverified |
| SWE-bench Verified Agentic Coding | 76.2% | Google — Gemini 3 Provendor | unverified |
| LiveCodeBench Coding | — | not evaluated | |
| MMLU-Pro Knowledge | — | not evaluated | |
| LMArena Elo Human Preference | 1,486 | LMArena (arena.ai)3rd-party | unverified |
| AA Intelligence Index Composite | 48 | Artificial Analysis3rd-party | unverified |
| Corporate Finance Finance | 63.7% | Vals AI — CorpFin v23rd-party | unverified |
| LegalBench Law | 87% | Vals AI — LegalBench3rd-party | unverified |
| TaxEval Tax & Accounting | 72.6% | Vals AI — TaxEval v23rd-party | unverified |
| Medical Coding Medicine | 52.2% | Vals AI — MedCode3rd-party | unverified |