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

Anthropic / Claude

Claude Sonnet 5.5

Version claude-sonnet-5-5 · Released 2026-09-28 · Available

Compare this model ↗
84QUANTUM SCORE

Explore Anthropic history →

INDEPENDENT BENCHMARK / SNAPSHOT 2026-10-16

Independent benchmark snapshot

This snapshot is over 14 days old. Review the dated benchmark records below for newer evidence.

Artificial Analysis Intelligence Index v4.3.2 · Higher is better. Selected models, sorted by this benchmark’s published score; equal scores are ties.

ModelAA Intelligence IndexTested effortEvidence
Claude Sonnet 5.556Max, default fallbackIndependent result ↗

This is a dated snapshot from one independent evaluator, on its own scale—not a Quantum Score or a complete market ranking. A missing Quantum Score means our broader evidence requirements are unmet; it does not mean the model is worse. Test dates are not published in these source summaries.

THE PRACTICAL READ

Should you shortlist Claude Sonnet 5.5?

Evidence checked 2026-11-07. This interpretation uses the cited records below; it is not a hands-on review.

What the evidence supports

The strongest relative category results in our current evidence are coding and reasoning. Scores describe this comparison pool, not a percentage of real-world tasks solved.

11 current independent benchmark observations. Several tasks from one suite do not count as separate independent sources.

What remains uncertain

Comparable category scores are missing for multimodal. Writing quality, factual accuracy, privacy and production reliability require separate evaluation.

An overall score summarizes covered categories; a high overall score may not match your priorities. Check the effort level and tool configuration before comparing results.

Inspect coverage →

Cost and response time

At 10M input + 2M output tokens, the base API estimate is $40.00/month. This excludes tools, caching, batch rates, subscriptions and taxes.

Output tokens per second measures generation after it starts. Reasoning time can make a fast-generating model take longer to finish. Use the measured speed and effort records below.

Estimate your actual usage →

Alternatives worth comparing

GPT-6 Luna

11 shared independent observations with matching test methods.

Same illustrative usage: $2.00/month ($38.00 less). Lower price does not establish equivalent task performance.

Compare tradeoffs →

Gemini 3.8 Flash

11 shared independent observations with matching test methods.

Same illustrative usage: $15.00/month ($25.00 less). Lower price does not establish equivalent task performance.

Compare tradeoffs →

Grok 4.6

11 shared independent observations with matching test methods.

Same illustrative usage: $32.00/month ($8.00 less). Lower price does not establish equivalent task performance.

Compare tradeoffs →

Follow changes to this model ↗ Choose an AI for coding → · Research guide → · Automation guide →

Coding95
Reasoning91
Math84
REVAL™
ⓘREVAL™ Research Evaluation Index — our proprietary 0–100 benchmark measuring real-world AI research performance. Methodology →
Not tested
Agents78
MultimodalNo data
SpeedNot measured
Value62

PROPRIETARY / RESEARCH EVALUATION INDEX

REVAL™ Not tested

Methodology →

This exact model version has not completed a reviewed REVAL evaluation. No score is assigned from reputation or external benchmarks.

01 / EVIDENCE

Benchmark breakdown

BenchmarkVersionMethodConfigurationResultTest dateVerifiedSource typeSource
Terminal-Bench 4.0 (reported best effort)Terminal-Bench 4.0 (reported best effort)Publisher-reported configuration; see source—70.6 %2026-09-282026-09-29provider first partyView source ↗
CursorBench 4.0 (reported best effort)CursorBench 4.0 (reported best effort)Publisher-reported configuration; see source—55.5 %2026-09-282026-09-29provider first partyView source ↗
FrontierCode 1.1 Main (reported best effort)FrontierCode 1.1 Main (reported best effort)Publisher-reported configuration; see source—46.2 %2026-09-282026-09-29provider first partyView source ↗
GDPval-AA v2.1 (reported best effort)GDPval-AA v2.1 (reported best effort)Publisher-reported configuration; see source—1844 Elo2026-09-282026-09-29provider first partyView source ↗
AA-Briefcase v1.1 (reported best effort)AA-Briefcase v1.1 (reported best effort)Publisher-reported configuration; see source—1811 Elo2026-09-282026-09-29provider first partyView source ↗
Humanity Last Exam (with tools; reported best effort)Humanity Last Exam (with tools; reported best effort)Publisher-reported configuration; see source—64.5 %2026-09-282026-09-29provider first partyView source ↗
OSWorld 2.1 (partial; reported best effort)OSWorld 2.1 (partial; reported best effort)Publisher-reported configuration; see source—80.1 %2026-09-282026-09-29provider first partyView source ↗
Chartography (no tools; reported best effort)Chartography (no tools; reported best effort)Publisher-reported configuration; see source—61.6 %2026-09-282026-09-29provider first partyView source ↗
Terminal-Bench 4.0 Vals mini-SWE-agent avg@3 fallbacks failed4.0Vals mini-SWE-agent avg@3; Anthropic fallbacks treated as failures—62.63 %2026-09-292026-09-29independent labView source ↗
LiveBench code_completion2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · claude-sonnet-5-5-max-effort86.957 %not published2026-10-17benchmark maintainerView source ↗
LiveBench code_generation2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · claude-sonnet-5-5-max-effort95.775 %not published2026-10-17benchmark maintainerView source ↗
LiveBench javascript2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · claude-sonnet-5-5-max-effort77.273 %not published2026-10-17benchmark maintainerView source ↗
LiveBench AMPS_Hard2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · claude-sonnet-5-5-max-effort98 %not published2026-10-17benchmark maintainerView source ↗
LiveBench olympiad2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · claude-sonnet-5-5-max-effort92.468 %not published2026-10-17benchmark maintainerView source ↗
LiveBench theory_of_mind2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · claude-sonnet-5-5-max-effort86.538 %not published2026-10-17benchmark maintainerView source ↗
LiveBench zebra_puzzle2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · claude-sonnet-5-5-max-effort100 %not published2026-10-17benchmark maintainerView source ↗
LiveBench 2.0 coding20261025LiveBench 2.0 published release tablePublished model configuration; effort not specified in table94.7 %not published2026-11-07benchmark maintainerView source ↗
LiveBench 2.0 reasoning20261025LiveBench 2.0 published release tablePublished model configuration; effort not specified in table91.6 %not published2026-11-07benchmark maintainerView source ↗
LiveBench 2.0 long_agentic20261025LiveBench 2.0 published release tablePublished model configuration; effort not specified in table63.4 %not published2026-11-07benchmark maintainerView source ↗

02 / COST

Price & speed

Input / 1M tokens $2.00

Output / 1M tokens $10.00

Cached input / 1M —

Batch input / 1M —

Batch output / 1M —

Speed No comparable observation yet

Price verified 2026-09-29

Price scope Base input/output rates; caching and batch tiers differ

Price source Official pricing ↗

02A / PERFORMANCE

Measured speed

No sourced speed measurement at a stated effort level yet.

03 / PROFILE

Capabilities

tool usevision

04 / CONTEXT

Evidence coverage & limits

Published tests describe specific environments and effort settings. They do not establish performance on every task. Read the practical interpretation above →

Coverage: 73% · Moderate confidence · 19 observations · 4 source domains (3 independent).

05 / HISTORY

Version & price history

Version claude-sonnet-5-5 · released 2026-09-28.

2026-09-29: $2.00 input / $10.00 output per 1M tokens · Price source ↗

06 / SOURCES

Source records

DATED EVIDENCE

History

Standard API price history

2026-09-292026-09-29
  • 2026-09-29: 4 USD / 1M · 75% input / 25% output USD per 1M · source ↗

One observation; no trend can be inferred.

Terminal-Bench 4.0 (reported best effort) / Terminal-Bench 4.0 (reported best effort) / %

2026-09-282026-09-28
  • 2026-09-28: 70.6 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

CursorBench 4.0 (reported best effort) / CursorBench 4.0 (reported best effort) / %

2026-09-282026-09-28
  • 2026-09-28: 55.5 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

FrontierCode 1.1 Main (reported best effort) / FrontierCode 1.1 Main (reported best effort) / %

2026-09-282026-09-28
  • 2026-09-28: 46.2 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

GDPval-AA v2.1 (reported best effort) / GDPval-AA v2.1 (reported best effort) / Elo

2026-09-282026-09-28
  • 2026-09-28: 1,844 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

AA-Briefcase v1.1 (reported best effort) / AA-Briefcase v1.1 (reported best effort) / Elo

2026-09-282026-09-28
  • 2026-09-28: 1,811 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

Humanity Last Exam (with tools; reported best effort) / Humanity Last Exam (with tools; reported best effort) / %

2026-09-282026-09-28
  • 2026-09-28: 64.5 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

OSWorld 2.1 (partial; reported best effort) / OSWorld 2.1 (partial; reported best effort) / %

2026-09-282026-09-28
  • 2026-09-28: 80.1 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

Chartography (no tools; reported best effort) / Chartography (no tools; reported best effort) / %

2026-09-282026-09-28
  • 2026-09-28: 61.6 result · Publisher-reported configuration; see source · source ↗

One observation; no trend can be inferred.

Terminal-Bench 4.0 Vals mini-SWE-agent avg@3 fallbacks failed / 4.0 / %

2026-09-292026-09-29
  • 2026-09-29: 62.63 result · Vals mini-SWE-agent avg@3; Anthropic fallbacks treated as failures · source ↗

One observation; no trend can be inferred.

LiveBench code_completion / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 86.957 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench code_generation / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 95.775 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench javascript / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 77.273 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench AMPS_Hard / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 98 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench olympiad / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 92.468 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench theory_of_mind / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 86.538 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench zebra_puzzle / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 100 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench 2.0 coding / 20261025 / %

2026-11-072026-11-07
  • 2026-11-07: 94.7 result · LiveBench 2.0 published release table · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench 2.0 reasoning / 20261025 / %

2026-11-072026-11-07
  • 2026-11-07: 91.6 result · LiveBench 2.0 published release table · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench 2.0 long_agentic / 20261025 / %

2026-11-072026-11-07
  • 2026-11-07: 63.4 result · LiveBench 2.0 published release table · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

coding category score history

2026-09-302026-11-07
  • 2026-09-30: 100 score · Scoring 3.0.0
  • 2026-10-01: 100 score · Scoring 3.0.0
  • 2026-10-02: 100 score · Scoring 3.0.0
  • 2026-10-03: 100 score · Scoring 3.0.0
  • 2026-10-04: 100 score · Scoring 3.0.0
  • 2026-10-05: 100 score · Scoring 3.0.0
  • 2026-10-06: 100 score · Scoring 3.0.0
  • 2026-10-07: 100 score · Scoring 3.0.0
  • 2026-10-08: 100 score · Scoring 3.0.0
  • 2026-10-09: 100 score · Scoring 3.0.0
  • 2026-10-10: 100 score · Scoring 3.0.0
  • 2026-10-11: 100 score · Scoring 3.0.0
  • 2026-10-12: 100 score · Scoring 3.0.0
  • 2026-10-13: 100 score · Scoring 3.0.0
  • 2026-10-14: 100 score · Scoring 3.0.0
  • 2026-10-15: 100 score · Scoring 3.0.0
  • 2026-10-16: 100 score · Scoring 3.0.0
  • 2026-10-17: 100 score · Scoring 3.0.0
  • 2026-10-18: 100 score · Scoring 3.0.0
  • 2026-10-19: 100 score · Scoring 3.0.0
  • 2026-10-20: 100 score · Scoring 3.0.0
  • 2026-10-21: 100 score · Scoring 3.0.0
  • 2026-10-22: 100 score · Scoring 3.0.0
  • 2026-10-23: 100 score · Scoring 3.0.0
  • 2026-10-24: 100 score · Scoring 3.0.0
  • 2026-10-25: 100 score · Scoring 3.0.0
  • 2026-10-26: 100 score · Scoring 3.0.0
  • 2026-10-27: 100 score · Scoring 3.0.0
  • 2026-10-28: 100 score · Scoring 3.0.0
  • 2026-10-29: 100 score · Scoring 3.0.0
  • 2026-10-30: 100 score · Scoring 3.0.0
  • 2026-10-31: 100 score · Scoring 3.0.0
  • 2026-11-01: 100 score · Scoring 3.0.0
  • 2026-11-02: 100 score · Scoring 3.0.0
  • 2026-11-03: 100 score · Scoring 3.0.0
  • 2026-11-04: 100 score · Scoring 3.0.0
  • 2026-11-05: 100 score · Scoring 3.0.0
  • 2026-11-06: 100 score · Scoring 3.0.0
  • 2026-11-07: 100 score · Scoring 3.0.0

reasoning category score history

2026-10-012026-11-07
  • 2026-10-01: 100 score · Scoring 3.0.0
  • 2026-10-02: 100 score · Scoring 3.0.0
  • 2026-10-03: 100 score · Scoring 3.0.0
  • 2026-10-04: 100 score · Scoring 3.0.0
  • 2026-10-05: 100 score · Scoring 3.0.0
  • 2026-10-06: 100 score · Scoring 3.0.0
  • 2026-10-07: 100 score · Scoring 3.0.0
  • 2026-10-08: 100 score · Scoring 3.0.0
  • 2026-10-09: 100 score · Scoring 3.0.0
  • 2026-10-10: 100 score · Scoring 3.0.0
  • 2026-10-11: 100 score · Scoring 3.0.0
  • 2026-10-12: 100 score · Scoring 3.0.0
  • 2026-10-13: 100 score · Scoring 3.0.0
  • 2026-10-14: 100 score · Scoring 3.0.0
  • 2026-10-15: 100 score · Scoring 3.0.0
  • 2026-10-16: 100 score · Scoring 3.0.0
  • 2026-10-17: 100 score · Scoring 3.0.0
  • 2026-10-18: 100 score · Scoring 3.0.0
  • 2026-10-19: 100 score · Scoring 3.0.0
  • 2026-10-20: 100 score · Scoring 3.0.0
  • 2026-10-21: 100 score · Scoring 3.0.0
  • 2026-10-22: 100 score · Scoring 3.0.0
  • 2026-10-23: 100 score · Scoring 3.0.0
  • 2026-10-24: 100 score · Scoring 3.0.0
  • 2026-10-25: 100 score · Scoring 3.0.0
  • 2026-10-26: 100 score · Scoring 3.0.0
  • 2026-10-27: 100 score · Scoring 3.0.0
  • 2026-10-28: 100 score · Scoring 3.0.0
  • 2026-10-29: 100 score · Scoring 3.0.0
  • 2026-10-30: 100 score · Scoring 3.0.0
  • 2026-10-31: 100 score · Scoring 3.0.0
  • 2026-11-01: 100 score · Scoring 3.0.0
  • 2026-11-02: 100 score · Scoring 3.0.0
  • 2026-11-03: 100 score · Scoring 3.0.0
  • 2026-11-04: 100 score · Scoring 3.0.0
  • 2026-11-05: 100 score · Scoring 3.0.0
  • 2026-11-06: 100 score · Scoring 3.0.0
  • 2026-11-07: 100 score · Scoring 3.0.0

math category score history

2026-10-012026-11-07
  • 2026-10-01: 84 score · Scoring 3.0.0
  • 2026-10-02: 84 score · Scoring 3.0.0
  • 2026-10-03: 84 score · Scoring 3.0.0
  • 2026-10-04: 84 score · Scoring 3.0.0
  • 2026-10-05: 84 score · Scoring 3.0.0
  • 2026-10-06: 84 score · Scoring 3.0.0
  • 2026-10-07: 84 score · Scoring 3.0.0
  • 2026-10-08: 84 score · Scoring 3.0.0
  • 2026-10-09: 84 score · Scoring 3.0.0
  • 2026-10-10: 84 score · Scoring 3.0.0
  • 2026-10-11: 84 score · Scoring 3.0.0
  • 2026-10-12: 84 score · Scoring 3.0.0
  • 2026-10-13: 84 score · Scoring 3.0.0
  • 2026-10-14: 84 score · Scoring 3.0.0
  • 2026-10-15: 84 score · Scoring 3.0.0
  • 2026-10-16: 84 score · Scoring 3.0.0
  • 2026-10-17: 84 score · Scoring 3.0.0
  • 2026-10-18: 84 score · Scoring 3.0.0
  • 2026-10-19: 84 score · Scoring 3.0.0
  • 2026-10-20: 84 score · Scoring 3.0.0
  • 2026-10-21: 84 score · Scoring 3.0.0
  • 2026-10-22: 84 score · Scoring 3.0.0
  • 2026-10-23: 84 score · Scoring 3.0.0
  • 2026-10-24: 84 score · Scoring 3.0.0
  • 2026-10-25: 84 score · Scoring 3.0.0
  • 2026-10-26: 84 score · Scoring 3.0.0
  • 2026-10-27: 84 score · Scoring 3.0.0
  • 2026-10-28: 84 score · Scoring 3.0.0
  • 2026-10-29: 84 score · Scoring 3.0.0
  • 2026-10-30: 84 score · Scoring 3.0.0
  • 2026-10-31: 84 score · Scoring 3.0.0
  • 2026-11-01: 84 score · Scoring 3.0.0
  • 2026-11-02: 84 score · Scoring 3.0.0
  • 2026-11-03: 84 score · Scoring 3.0.0
  • 2026-11-04: 84 score · Scoring 3.0.0
  • 2026-11-05: 84 score · Scoring 3.0.0
  • 2026-11-06: 84 score · Scoring 3.0.0
  • 2026-11-07: 84 score · Scoring 3.0.0

agents category score history

2026-10-012026-11-07
  • 2026-10-01: 80 score · Scoring 3.0.0
  • 2026-10-02: 80 score · Scoring 3.0.0
  • 2026-10-03: 80 score · Scoring 3.0.0
  • 2026-10-04: 80 score · Scoring 3.0.0
  • 2026-10-05: 80 score · Scoring 3.0.0
  • 2026-10-06: 80 score · Scoring 3.0.0
  • 2026-10-07: 80 score · Scoring 3.0.0
  • 2026-10-08: 80 score · Scoring 3.0.0
  • 2026-10-09: 80 score · Scoring 3.0.0
  • 2026-10-10: 80 score · Scoring 3.0.0
  • 2026-10-11: 80 score · Scoring 3.0.0
  • 2026-10-12: 80 score · Scoring 3.0.0
  • 2026-10-13: 80 score · Scoring 3.0.0
  • 2026-10-14: 80 score · Scoring 3.0.0
  • 2026-10-15: 80 score · Scoring 3.0.0
  • 2026-10-16: 80 score · Scoring 3.0.0
  • 2026-10-17: 80 score · Scoring 3.0.0
  • 2026-10-18: 80 score · Scoring 3.0.0
  • 2026-10-19: 80 score · Scoring 3.0.0
  • 2026-10-20: 80 score · Scoring 3.0.0
  • 2026-10-21: 80 score · Scoring 3.0.0
  • 2026-10-22: 80 score · Scoring 3.0.0
  • 2026-10-23: 80 score · Scoring 3.0.0
  • 2026-10-24: 80 score · Scoring 3.0.0
  • 2026-10-25: 80 score · Scoring 3.0.0
  • 2026-10-26: 80 score · Scoring 3.0.0
  • 2026-10-27: 80 score · Scoring 3.0.0
  • 2026-10-28: 80 score · Scoring 3.0.0
  • 2026-10-29: 80 score · Scoring 3.0.0
  • 2026-10-30: 80 score · Scoring 3.0.0
  • 2026-10-31: 80 score · Scoring 3.0.0
  • 2026-11-01: 80 score · Scoring 3.0.0
  • 2026-11-02: 80 score · Scoring 3.0.0
  • 2026-11-03: 80 score · Scoring 3.0.0
  • 2026-11-04: 80 score · Scoring 3.0.0
  • 2026-11-05: 80 score · Scoring 3.0.0
  • 2026-11-06: 80 score · Scoring 3.0.0
  • 2026-11-07: 80 score · Scoring 3.0.0

07 / EXPLORE

Similar models