Leaderboard
Language ModelsProprietary
Gemini 3.5 Flash
Google's current fast/default Gemini (GA); strong agentic performance.
Crosshair Index
68.8
#13 of 32 · Language Models
- Provider
- Google DeepMind
- Released
- 2026-05-19
- Parameters
- Undisclosed
- Context
- 1.048576M tokens
Token pricing
- Input
- $1.5 /1M
- Output
- $9 /1M
- Cache read
- $0.15 /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.
Accounting & Audit
70
skill
Numerically exact work over tax and financial documents — reconciliation, controls, and the arithmetic discipline audits demand.
Scorecard
| Benchmark | Score | Source | Status |
|---|---|---|---|
| GPQA Diamond Reasoning | — | not evaluated | |
| Humanity's Last Exam Frontier | 40.2% | Google — Gemini 3.5 Flashvendor | unverified |
| SWE-bench Verified Agentic Coding | — | not evaluated | |
| LiveCodeBench Coding | — | not evaluated | |
| MMLU-Pro Knowledge | — | not evaluated | |
| LMArena Elo Human Preference | 1,477 | LMArena (arena.ai)3rd-party | unverified |
| AA Intelligence Index Composite | 55 | Artificial Analysis3rd-party | unverified |
| Corporate Finance Finance | 64.7% | Vals AI — CorpFin v23rd-party | unverified |
| LegalBench Law | 83.6% | Vals AI — LegalBench3rd-party | unverified |
| TaxEval Tax & Accounting | 74.4% | Vals AI — TaxEval v23rd-party | unverified |
| Medical Coding Medicine | 55.8% | Vals AI — MedCode3rd-party | unverified |