ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Opus 4.8vsGPT-5.5

GPT-5.5 leads 5 of 10 shared benchmarks. Claude Opus 4.8 is 1.2x cheaper per token. Both offer a 1M-token context window.

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
4 – 5
GPT-5.5 leads · 1 tied
Cheaper per token
Claude Opus 4.8
1.2x cheaper, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
100% · 95.2941%
Anthropic · OpenAI
Claude Opus 4.8
Anthropic · released 2026-05-28
textvision
Context
1M
Max out
128K
Input /1M
$5
Output /1M
$25
Cached /1M
$0.5
Scores
17 · 13 core
GPT-5.5
OpenAI · released 2026-04-23
textvision
Context
1M
Max out
128K
Input /1M
$5
Output /1M
$30
Cached /1M
$0.5
Scores
21 · 10 core
Quality

Benchmark matrix

BenchmarkClaude Opus 4.8GPT-5.5ΔEdge
Reported by both · 10
GPQA Diamond93.6% 90.7% epoch+2.9 ptClaude Opus 4.8
AIME 2026100% matharena100% matharena0Tie
LMArena Elo1452.7 1465.6 -12.9GPT-5.5
BrowseComp84.3% 84.4% -0.1 ptGPT-5.5
FrontierMath Tier 4 v2 (Epoch AI run)56.1% epoch72.5% epoch-16.4 ptGPT-5.5
FrontierMath Tiers 1-3 v2 (Epoch AI run)80% epoch85.3% epoch-5.3 ptGPT-5.5
OSWorld-Verified83.4% 78.7% +4.7 ptClaude Opus 4.8
OTIS Mock AIME 2024-2025 (Epoch AI run)98.3% epoch84.4% epoch+13.9 ptClaude Opus 4.8
SimpleQA Verified53% epoch63% epoch-10 ptGPT-5.5
SWE-Bench Pro69.2% 58.6% +10.6 ptClaude Opus 4.8
Only Claude Opus 4.8 reports · 6
SWE-bench Verified88.6% not reported
Humanity's Last Exam (no tools)49.8% not reported
Humanity's Last Exam (with tools)57.9% not reported
SWE-bench Multilingual84.4% not reported
SWE-bench Multimodal38.4% not reported
Terminal-Bench 2.174.6% not reported
Only GPT-5.5 reports · 11
ARC-AGI-1 (Verified)not reported95%
ARC-AGI-2 (Verified)not reported85%
FrontierMath Tier 1-3not reported51.7%
FrontierMath Tier 4not reported35.4%
GDPval (wins or ties)not reported84.9%
MCP Atlasnot reported75.3%
MMMU-Pro (no tools)not reported81.2%
MMMU-Pro (with tools)not reported83.2%
Tau2-bench Telecomnot reported98%
Terminal-Bench 2.0not reported82.7%
Toolathlonnot reported55.6%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude Opus 4.8 minus GPT-5.5 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecClaude Opus 4.8GPT-5.5Edge
Context window1M tokens1M tokensTie
Max output128K tokens128K tokensTie
Input price / 1M$5 $5 Tie
Output price / 1M$25 $30 Claude Opus 4.8
Cached input / 1M$0.5 $0.5 Tie
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$30$35Claude Opus 4.8
Modalitiestext · visiontext · visionTie
Released2026-05-282026-04-23
Cited benchmark scores1721
Reliability

Provider status

All providers
More matchups

Claude Opus 4.8 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Opus 4.8 and GPT-5.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.