Leaderboard
Language ModelsOpen weights
Llama 4 Maverick
Meta's open-weights MoE (~17B active); the current open Llama flagship.
Crosshair Index
54.1
#27 of 32 · Language Models
- Provider
- Meta AI
- Released
- 2025-04-05
- Parameters
- 400B
- Context
- 1M tokens
Token pricing
- Input
- $0.35 /1M
- Output
- $0.85 /1M
- Cache read
- $0.27 /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
79
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 | 69.8% | Meta — Llama 4vendor | unverified |
| Humanity's Last Exam Frontier | — | not evaluated | |
| SWE-bench Verified Agentic Coding | — | not evaluated | |
| LiveCodeBench Coding | 43.4% | Meta — Llama 4vendor | unverified |
| MMLU-Pro Knowledge | 80.5% | Meta — Llama 4vendor | unverified |
| LMArena Elo Human Preference | — | not evaluated | |
| AA Intelligence Index Composite | 18 | Artificial Analysis3rd-party | unverified |
| Corporate Finance Finance | 49.7% | Vals AI — CorpFin v23rd-party | unverified |
| LegalBench Law | 77.8% | Vals AI — LegalBench3rd-party | unverified |
| TaxEval Tax & Accounting | 66.6% | Vals AI — TaxEval v23rd-party | unverified |
| Medical Coding Medicine | 36.5% | Vals AI — MedCode3rd-party | unverified |