THE SCOREBOARD FOR WHAT'S NEXTAI + QUANTUM, SCORED. COMPARED. EXPLAINED.
AIQUANTUMSCORE.

HEAD TO HEAD

Make the
right call.

Pick two to four models. Compare category evidence, price, context, speed and capabilities side by side.

Sign in to save this comparison →

01 / SCORECARD

Coding focus · side by side

MetricClaude Opus 5.5Claude Sonnet 5.5
Quantum Score86QUANTUM SCORE88QUANTUM SCORE
Confidence / coverageModerate confidence · 73% · 3 independent domainsModerate confidence · 73% · 2 independent domains
Context window1,000,000 tokens1,000,000 tokens
Modalities / toolstext, image · tool use, visiontext, image · tool use, vision
Coding87100 +13 vs first
Reasoning97100 +3 vs first
Math9284 -8 vs first
Research——
Agents10080 -20 vs first
Multimodal——
Speed——
Value5265 +13 vs first
Input / 1M$4.00$2.00
Output / 1M$20.00$10.00
Measured output speed92 tokens/s · Max effort—

02 / EVIDENCE

Published benchmark evidence

BenchmarkClaude Opus 5.5Claude Sonnet 5.5
Terminal-Bench 4.0 (reported best effort) · Terminal-Bench 4.0 (reported best effort) · Publisher-reported configuration; see source66.4 %
provider first party ↗
70.6 %
provider first party ↗
CursorBench 4.0 (reported best effort) · CursorBench 4.0 (reported best effort) · Publisher-reported configuration; see source57.8 %
provider first party ↗
55.5 %
provider first party ↗
FrontierCode 1.1 Main (reported best effort) · FrontierCode 1.1 Main (reported best effort) · Publisher-reported configuration; see source54.4 %
provider first party ↗
46.2 %
provider first party ↗
GDPval-AA v2.1 (reported best effort) · GDPval-AA v2.1 (reported best effort) · Publisher-reported configuration; see source1846 Elo
provider first party ↗
1844 Elo
provider first party ↗
AA-Briefcase v1.1 (reported best effort) · AA-Briefcase v1.1 (reported best effort) · Publisher-reported configuration; see source1822 Elo
provider first party ↗
1811 Elo
provider first party ↗
Humanity Last Exam (with tools; reported best effort) · Humanity Last Exam (with tools; reported best effort) · Publisher-reported configuration; see source67.7 %
provider first party ↗
64.5 %
provider first party ↗
OSWorld 2.1 (partial; reported best effort) · OSWorld 2.1 (partial; reported best effort) · Publisher-reported configuration; see source81.8 %
provider first party ↗
80.1 %
provider first party ↗
Chartography (no tools; reported best effort) · Chartography (no tools; reported best effort) · Publisher-reported configuration; see source64.4 %
provider first party ↗
61.6 %
provider first party ↗
Terminal-Bench 4.0 Vals mini-SWE-agent avg@3 fallbacks failed · 4.0 · Vals mini-SWE-agent avg@3; Anthropic fallbacks treated as failures58.08 %
independent lab ↗
62.63 %
independent lab ↗
LiveBench code_completion · 2026-06-25 · Public table; published model effort variant86.957 %
benchmark maintainer ↗
86.957 %
benchmark maintainer ↗
LiveBench code_generation · 2026-06-25 · Public table; published model effort variant91.549 %
benchmark maintainer ↗
95.775 %
benchmark maintainer ↗
LiveBench javascript · 2026-06-25 · Public table; published model effort variant81.818 %
benchmark maintainer ↗
77.273 %
benchmark maintainer ↗
LiveBench AMPS_Hard · 2026-06-25 · Public table; published model effort variant98 %
benchmark maintainer ↗
98 %
benchmark maintainer ↗
LiveBench olympiad · 2026-06-25 · Public table; published model effort variant93.251 %
benchmark maintainer ↗
92.468 %
benchmark maintainer ↗
LiveBench theory_of_mind · 2026-06-25 · Public table; published model effort variant84.615 %
benchmark maintainer ↗
86.538 %
benchmark maintainer ↗
LiveBench zebra_puzzle · 2026-06-25 · Public table; published model effort variant100 %
benchmark maintainer ↗
100 %
benchmark maintainer ↗

AS THE EVIDENCE CHANGED

Comparison history

Dated releases, price events, and benchmark publications. A price or test change can alter the factual comparison; this timeline does not pick a winner.

2026-09-28 · Claude Sonnet 5.5 released ↗ · source

2026-09-22 · Claude Opus 5.5 released ↗ · source

2026-09-30 verified (test date not published) · claude-opus-5-5 entered LiveBench code_completion (2026-06-25) at 86.957 % · source ↗

2026-09-30 verified (test date not published) · claude-opus-5-5 entered LiveBench code_generation (2026-06-25) at 91.549 % · source ↗

2026-09-30 verified (test date not published) · claude-opus-5-5 entered LiveBench javascript (2026-06-25) at 81.818 % · source ↗

2026-09-30 verified (test date not published) · claude-opus-5-5 entered LiveBench AMPS_Hard (2026-06-25) at 98 % · source ↗

2026-09-30 verified (test date not published) · claude-opus-5-5 entered LiveBench olympiad (2026-06-25) at 93.251 % · source ↗

2026-09-30 verified (test date not published) · claude-opus-5-5 entered LiveBench theory_of_mind (2026-06-25) at 84.615 % · source ↗

2026-09-30 verified (test date not published) · claude-opus-5-5 entered LiveBench zebra_puzzle (2026-06-25) at 100 % · source ↗

2026-09-30 verified (test date not published) · claude-sonnet-5-5 entered LiveBench code_completion (2026-06-25) at 86.957 % · source ↗

2026-09-30 verified (test date not published) · claude-sonnet-5-5 entered LiveBench code_generation (2026-06-25) at 95.775 % · source ↗

2026-09-30 verified (test date not published) · claude-sonnet-5-5 entered LiveBench javascript (2026-06-25) at 77.273 % · source ↗

2026-09-30 verified (test date not published) · claude-sonnet-5-5 entered LiveBench AMPS_Hard (2026-06-25) at 98 % · source ↗

2026-09-30 verified (test date not published) · claude-sonnet-5-5 entered LiveBench olympiad (2026-06-25) at 92.468 % · source ↗

An overall score appears only after enough current, comparable, independently sourced results exist. Pricing and individual benchmark results remain visible meanwhile.