Compare

Claude Opus 4.8 vs EXAONE 4.5

Claude Opus 4.8 (Anthropic) and EXAONE 4.5 (LG AI Research) compared on benchmarks, pricing, context window, and use-case rankings.

Claude Opus 4.8Anthropic · 1 in the newsEXAONE 4.5LG AI Research

Scores

Intelligence (ECI)157—

Coding93—

Math91—

Reasoning & Knowledge75—

Agentic & Tools94—

Specifications

DeveloperAnthropicLG AI Research

FamilyClaude—

ReleasedMay 28, 2026Apr 9, 2026

Parameters—33.2B

AvailabilityAPI accessOpen weights (restricted use)

Context window1M—

Price — $/M input$5.00—

Price — $/M output$25.00—

Inputstext, image, file—

Outputstext—

Benchmarks

AIME 2024/202598%—

APEX43%—

ARC-AGI93%—

ARC-AGI-272%—

FrontierMath47%—

FrontierMath Tier 431%—

GPQA Diamond91%—

SimpleBench65%—

SimpleQA Verified40%—

WebDev Arena1552—

WeirdML83%—

Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.

Want a different match-up? Open the compare tool to add or swap models.

More comparisons

Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.