Llama 3.2 Instruct 90B (Vision)
Context 128K tokens
Providers
No provider publishes an API price for this model yet, so no cost can be modeled.
Composite
1 of 7 inputs6 radar axes: DesignArena's two boards share one2.7
Thin data · 1/7Based on only 1 of 7 Composite inputs — treat this rank as uncertaindominance-adjusted from 4.5: a better-measured model that is at least as good on each of these inputs ranks above it
AA Coding v4.x —Coding Agent v1.4 —AA Intelligence (est.) 2.7AA Agentic —Epoch ECI —Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
4 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
Knowledge
Humanity's Last Exam (AA text-only)224.5%
Humanity's Last Exam (AA text-only) published 2026-09-10 → · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
Science
GPQA Diamond (AA)1843.2%
GPQA Diamond (AA) published 2026-09-10 → · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
Vision
MMMU Pro (AA)639.5%
MMMU Pro (AA) published 2026-09-10 → · Published board — Tests multimodal understanding using challenging ten-option questions.
CharXiv Reasoning val-v1.04337.5%
CharXiv Reasoning val-v1.0 → · validation — Can a multimodal model reason over the real, messy charts in scientific papers — combining values, trends and labels across a figure — rather than read off templated plots?
Missing coverage · 315 benchmark versions
No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.