Frontier BenchSI model benchmarks · Jul 2026
ModelsCompareLabsMethodology
All models
MA

Llama 4 Scout

Meta AI

10M-token context — the only realistic choice for whole-repo or whole-corpus input.

Open-weightLlama license10M contextReleased Jan 2026textvisioncode

API price · per 1M tokens

$0.15/$0.45

input / output

≈ $0.22/M blended

Benchmarks

Bar shows this model's score; tick shows the best score across all tracked models for context.

SWE-bench VerifiedReal GitHub issues, human-verified patches. The standard coding-agent benchmark.
55.0/ best 90.1
GPQA DiamondGoogle-proof graduate-level science Q&A. General reasoning proxy.
72.0/ best 94.4
MMLU-ProMulti-task language understanding across 120+ academic subjects.
75.0/ best 93.0
HumanEval+Functional code generation from docstrings.
82.0/ best 96.0
MATH-500Competition-style math problems.
78.0/ best 97.8

Other Meta AI models

MA

Llama 4 Maverick

Open-weight

≈$0.30/M

Built by GLM-5.2 · Scores are directional, drawn from public mid-2026 benchmarks.

SWE-bench, GPQA, MMLU, AIME, HLE etc. are trademarks of their respective owners.