Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Claude Opus 4.8 vs GPT-5.6 Luna

52 SHARED BENCHMARKS

Across 52 shared benchmarks, Claude Opus 4.8 scores higher on 40 and GPT-5.6 Luna on 12. The widest gap is ARC-AGI-3, where Claude Opus 4.8 scores 1.5 against 0.2. GPT-5.6 Luna is the cheaper of the two on tracked API pricing ($0.20 against $5.00 per million input tokens).

ANTHROPICVSOPENAI52 SHARED40–12 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

MakerAnthropicOpenAI
Released
Price per 1M tokens input / output$5.00 / $25.00$0.20 / $1.20
Cost of 1M in + 1M out$30.00$1.40 21.4× less
Head-to-head of 52 shared benchmarks40 wins12 wins
Scores tracked independently verified200 32 ◆201 43 ◆

Release dates per Artificial Analysis. Prices: Artificial Analysis for Claude Opus 4.8; OpenAI's own price page for GPT-5.6 Luna. ◆ = independently verified score.

Where each leadsby capability area · benchmark wins

AreaClaude Opus 4.8WINSGPT-5.6 Luna
Reasoning70Claude Opus 4.8 leads 7 of 7 · widest: SimpleBench 64.8 vs 46.8
Coding52Claude Opus 4.8 leads 5 of 7 · widest: SWE-bench Pro 69.2 vs 62.7
Agentic51Claude Opus 4.8 leads 5 of 6 · widest: Terminal-Bench 4.0 21.7 vs 11.6
Factuality30Claude Opus 4.8 leads 3 of 3 · widest: AA-Omniscience · Non-hallucination 60.7 vs 7.4
Instruction Following10Claude Opus 4.8 leads 1 of 1 · widest: LiveBench · Instruction Following 72 vs 60.1
Long Context01GPT-5.6 Luna leads 1 of 1 · widest: AA-LCR 77.7 vs 83.7
Math23GPT-5.6 Luna leads 3 of 5 · widest: HMMT Feb. 2026 95.5 vs 98.5
Multimodal20Claude Opus 4.8 leads 2 of 2 · widest: CharXiv (RQ) 89.9 vs 82.7

Biggest gaps

Claude Opus 4.8 pulls furthest ahead on

  1. AA-Omniscience · Non-hallucination60.7 vs 7.4
  2. Terminal-Bench 4.021.7 vs 11.6
  3. SimpleBench64.8 vs 46.8

GPT-5.6 Luna pulls furthest ahead on

  1. AA-LCR83.7 vs 77.7
  2. SWE-bench Verified93 vs 88.6
  3. HMMT Feb. 202698.5 vs 95.5

Every shared benchmark52 · grouped by area

Reasoning 7

ARC-AGI-31.50.2
ARC-AGI-272.1◆ 59.6
CritPt20.920.6
LiveBench · Reasoning89.2 ◆◆ 85.6
SimpleBench64.8 ◆◆ 46.8

Coding 7

Agentic 6

BrowseComp84.383.3
GDPVal46.947.2
Terminal-Bench 4.021.711.6

Instruction Following 1

Long Context 1

AA-LCR77.783.7

Math 5

AIME 2026100 ◆97.6
HMMT Feb. 202695.5 ◆98.5
LiveBench · Mathematics94.3 ◆◆ 87.2

Multimodal 2

LMArena · Vision1295 ◆◆ 1259
CharXiv (RQ)89.982.7

Other shared benchmarks 20

Each score is the one the model's own page shows — the most authoritative tracked result for that benchmark, on the benchmark's standard methodology (source-attributed). ↓ marks lower-is-better metrics; ◆ an independently verified score. Open either model for its full surface, provenance and pricing. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (direct, openai-official), otherwise the lowest tracked offer.

Compare Claude Opus 4.8 withALL PAIRINGS →

Compare GPT-5.6 Luna withALL PAIRINGS →