AI Flash Report

Claude Opus 4.8 vs GPT-5.5 Instant: Benchmarks, Pricing & Capabilities Compared

TL;DR — Claude Opus 4.8 wins for reasoning + long-context · GPT-5.5 Instant wins for general use.

Claude Opus 4.8 Anthropic
Released
2026-05-28
Context window
1M tokens
Input price
$6.25 / Mtok
Output price
$25.00 / Mtok
Released
2026-05-05
Context window
400K tokens
Input price
$5.00 / Mtok
Output price
$30.00 / Mtok

Benchmark comparison

Benchmark Claude Opus 4.8 GPT-5.5 Instant
AA Intelligence Index 61.4 41.8
GPQA Diamond 92.0% 84.6%
HLE 45.7% 20.3%
IF-Bench 62.2% 71.5%
LiveCodeBench Reasoning 67.7% 55.7%
SciCode 53.5% 50.3%
TAU2-bench 94.4% 49.4%
TerminalBench-Hard 58.3% 42.4%

Pricing comparison

Metric Claude Opus 4.8 GPT-5.5 Instant
Input ($/Mtok) $6.25 $5.00
Output ($/Mtok) $25.00 $30.00
Cached input ($/Mtok)
Cost per 1M-token roundtrip (1M in + 1M out) $31.25 $35.00

Context window & modalities

Attribute Claude Opus 4.8 GPT-5.5 Instant
Context window 1M tokens 400K tokens
Input modalities text, image text, image
Output modalities text text
Knowledge cutoff 2025-08-31

Verdict by use case

Coding
Insufficient data
Basis: SWE-bench

No shared coding benchmark.

Reasoning
→ Claude Opus 4.8
Basis: GPQA Diamond

Claude Opus 4.8 92% vs GPT-5.5 Instant 84.6% on GPQA Diamond.

Math
Insufficient data
Basis: MATH / AIME

No shared math benchmark.

Long context
→ Claude Opus 4.8
Basis: Context window

Claude Opus 4.8 1M tokens vs GPT-5.5 Instant 400K tokens.

Cost
→ GPT-5.5 Instant
Basis: Input $/Mtok

Claude Opus 4.8 $6.25/Mtok vs GPT-5.5 Instant $5/Mtok input.

Changelog & releases

Claude Opus 4.8
Released 2026-05-28
GPT-5.5 Instant
Released 2026-05-05

Related comparisons