Claude Opus 5.5vsClaude Opus 5

SI Score, benchmarks, price and context compared, with every number sourced.

78.4
SI Score
#2 of 142 ranked models

Anthropic 100% confidence 100 percent, Full confidence

74.9
SI Score
#5 of 142 ranked models

Anthropic 100% confidence 100 percent, Full confidence

Pillar by pillar

Claude Opus 5.5Claude Opus 5
91.4 Reasoning30% of score 84.3
91.5 Math15% of score 86.9
72.5 Coding40% of score 69.7
82.8 Preference15% of score 82.0

The basics

AttributeClaude Opus 5.5Claude Opus 5
Input price, per 1M tokens $4.00Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		$5.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded Retrieved Oct 9, 2026 · factual citation
Open source ↗
Output price, per 1M tokens $20.00Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		$25.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded Retrieved Oct 9, 2026 · factual citation
Open source ↗
Context window 1MAnthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		1Mmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released Sep 22, 2026Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		Jul 24, 2026models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Weights Closed Closed

Highlighted values are the lower price or the larger context window.

Shared benchmarks

27 in common. Best result ahead: Claude Opus 5.5 on 17, Claude Opus 5 on 8

Each side shows its best published result. Results can come from different settings or harnesses, so open a row to compare like with like before reading much into a small gap.

ARC-AGI-1 (public eval) 98.6% 99%

Claude Opus 5.5

  • low effort92.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • medium effort98.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • high effort98.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • xhigh effort98.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • max effort98.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] anthropic-claude-opus-5-5-maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗

Claude Opus 5

  • high effort99%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • max effort99%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' output effort. [variant] anthropic-claude-opus-5-maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-1 (public eval)
ARC-AGI-1 (semi-private) 98.5% 97.5%

Claude Opus 5.5

  • low effort88.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • medium effort97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • high effort98.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • xhigh effort97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • max effort97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] anthropic-claude-opus-5-5-maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗

Claude Opus 5

  • high effort97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • max effort97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' output effort. [variant] anthropic-claude-opus-5-maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-1 (semi-private)
ARC-AGI-2 (public eval) 97.9% 97.1%

Claude Opus 5.5

  • low effort67.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • medium effort93.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • high effort93.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • xhigh effort97.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • max effort97.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] anthropic-claude-opus-5-5-maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗

Claude Opus 5

  • high effort93.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • max effort97.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' output effort. [variant] anthropic-claude-opus-5-maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-2 (public eval)
ARC-AGI-2 (semi-private) 93.3% 90.4%

Claude Opus 5.5

  • low effort70.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • medium effort87.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • high effort93.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • xhigh effort92.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. [variant] anthropic-claude-opus-5-5-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • max effort91.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] anthropic-claude-opus-5-5-maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗

Claude Opus 5

  • high effort88.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • max effort90.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' output effort. [variant] anthropic-claude-opus-5-maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-2 (semi-private)
FrontierMath Tier 4 (v2) 95% 73.2%

Claude Opus 5.5

  • max effort95%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 22, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗

Claude Opus 5

  • max effort73.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 24, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About FrontierMath Tier 4 (v2)
FrontierMath Tiers 1–3 (v2) 91.2% 85.6%

Claude Opus 5.5

  • max effort91.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 22, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗

Claude Opus 5

  • max effort85.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 24, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About FrontierMath Tiers 1–3 (v2)
GPQA Diamond 90.6% 93.9%

Claude Opus 5.5

  • max effort90.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 22, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗

Claude Opus 5

  • low effort87.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • max effort93.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 24, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 392.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About GPQA Diamond
Humanity's Last Exam (with tools) 67.7% 64.7%

Claude Opus 5.5

  • max effort67.7%Official model cards via models.devLab-reported; metric score; transcribed by MIT models.dev catalog; not independently evaluated [variant] max effort; with tools; production safeguards with fallbackPublished Sep 22, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
    Open source ↗

Claude Opus 5

  • Published result64.7%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] with toolsPublished Jul 24, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
    Open source ↗
About Humanity's Last Exam (with tools)
LiveBench Coding: code completion 87.0% 82.6%

Claude Opus 5.5

  • Published result87.0%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result82.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Coding: code completion
LiveBench Coding: code generation 91.5% 80.3%

Claude Opus 5.5

  • Published result91.5%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result80.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Coding: code generation
LiveBench Coding: JavaScript 72.7% 77.3%

Claude Opus 5.5

  • Published result72.7%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result77.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Coding: JavaScript
LiveBench Coding: Python 70% 75%

Claude Opus 5.5

  • Published result70%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result75%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Coding: Python
LiveBench Coding: TypeScript 53.3% 43.3%

Claude Opus 5.5

  • Published result53.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result43.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Coding: TypeScript
LiveBench Math: AMPS Hard 99% 99.0%

Claude Opus 5.5

  • Published result99%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result99.0%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Math: AMPS Hard
LiveBench Math: competition math 97.1% 94.1%

Claude Opus 5.5

  • Published result97.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result94.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Math: competition math
LiveBench Math: integrals 99% 97%

Claude Opus 5.5

  • Published result99%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result97%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Math: integrals
LiveBench Math: olympiad 92.2% 92.8%

Claude Opus 5.5

  • Published result92.2%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result92.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Math: olympiad
LiveBench Math: simplify 63% 61.6%

Claude Opus 5.5

  • Published result63%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result61.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Math: simplify
LiveBench Reasoning: connections 99.3% 99.3%

Claude Opus 5.5

  • Published result99.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result99.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Reasoning: connections
LiveBench Reasoning: consecutive events 90.4% 77.6%

Claude Opus 5.5

  • Published result90.4%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result77.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Reasoning: consecutive events
LiveBench Reasoning: logic with navigation 80% 86%

Claude Opus 5.5

  • Published result80%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result86%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Reasoning: logic with navigation
LiveBench Reasoning: spatial 98% 100%

Claude Opus 5.5

  • Published result98%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Reasoning: spatial
LiveBench Reasoning: theory of mind 84.6% 78.8%

Claude Opus 5.5

  • Published result84.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result78.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Reasoning: theory of mind
LiveBench Reasoning: zebra puzzles 100% 100%

Claude Opus 5.5

  • Published result100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗

Claude Opus 5

  • Published result100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
    Open source ↗
About LiveBench Reasoning: zebra puzzles
LMArena Text 1514.8 elo 1502.6 elo

Claude Opus 5.5

  • Published result1514.8 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
    Open source ↗

Claude Opus 5

  • Published result1502.6 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
    Open source ↗
About LMArena Text
OTIS Mock AIME 2024–2025 100% 98.9%

Claude Opus 5.5

  • max effort100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 22, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗

Claude Opus 5

  • low effort93.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • max effort98.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 24, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 397.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About OTIS Mock AIME 2024–2025
Terminal-Bench 4.0 66.4% 53.9%

Claude Opus 5.5

  • xhigh effort66.4%Official model cards via models.devLab-reported; metric score; transcribed by MIT models.dev catalog; not independently evaluated [variant] xhigh effort; production safeguards with fallback; 4.0Published Sep 22, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
    Open source ↗
  • Setting 264.8%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · Apache-2.0; factual citation
    Open source ↗

Claude Opus 5

  • Setting 153.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; xhighPublished Sep 17, 2026 Retrieved Oct 9, 2026 · Apache-2.0; factual citation
    Open source ↗
  • Setting 251.8%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; maxPublished Sep 3, 2026 Retrieved Oct 9, 2026 · Apache-2.0; factual citation
    Open source ↗
  • Setting 350.3%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; highPublished Sep 17, 2026 Retrieved Oct 9, 2026 · Apache-2.0; factual citation
    Open source ↗
  • Setting 444.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; mediumPublished Sep 17, 2026 Retrieved Oct 9, 2026 · Apache-2.0; factual citation
    Open source ↗
  • Setting 534.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; lowPublished Sep 17, 2026 Retrieved Oct 9, 2026 · Apache-2.0; factual citation
    Open source ↗
About Terminal-Bench 4.0

Which should you choose?

  • For reasoning, Claude Opus 5.5 leads by 7.0 points.
  • For math, Claude Opus 5.5 leads by 4.6 points.
  • Claude Opus 5.5 costs less per input token ($4.00 vs $5.00 per 1M).
  • Confidence is 100% for Claude Opus 5.5 and 100% for Claude Opus 5; sources still to report can move either score.

These follow from the numbers above. They're not a verdict on your use case.

What changed

All releases · RSS feed

Alerts on this device

What to be alerted about
RSS feed