Leaderboard
Language ModelsProprietary
Grok 4.20
xAI Grok 4.20 (reasoning); multi-agent 'council' architecture, very long context.
Crosshair Index
65.6
#19 of 32 · Language Models
- Provider
- xAI
- Released
- 2026-03-10
- Parameters
- Undisclosed
- Context
- 2M tokens
Token pricing
- Input
- $2 /1M
- Output
- $6 /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.
Corporate Law
78
skill
Legal reasoning — issue spotting, rule application, and contract analysis — plus the broad knowledge a generalist counsel needs.
Scorecard
| Benchmark | Score | Source | Status |
|---|---|---|---|
| GPQA Diamond Reasoning | — | not evaluated | |
| Humanity's Last Exam Frontier | — | not evaluated | |
| SWE-bench Verified Agentic Coding | — | not evaluated | |
| LiveCodeBench Coding | — | not evaluated | |
| MMLU-Pro Knowledge | — | not evaluated | |
| LMArena Elo Human Preference | 1,473 | LMArena (arena.ai)3rd-party | unverified |
| AA Intelligence Index Composite | 49 | Artificial Analysis3rd-party | unverified |
| Corporate Finance Finance | 63.7% | Vals AI — CorpFin v23rd-party | unverified |
| LegalBench Law | 77.7% | Vals AI — LegalBench3rd-party | unverified |
| TaxEval Tax & Accounting | 74.1% | Vals AI — TaxEval v23rd-party | unverified |
| Medical Coding Medicine | 32.2% | Vals AI — MedCode3rd-party | unverified |