Sign Up

Claude Opus 5.5

Anthropic
1Announcement
Claude Opus 5.5 launch post cover

Cost/1M tokens

input
$4.00
cached
$0.20
output
$20.00
cache write
$5.00
Context
1Mtokens
Released
1mo ago

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Arena leaderboards and other sourced evaluations appear below; missing scores are not zero.

How it ranks

Against its predecessor, similarly priced models and the models ranked around it.

DeepSWE 1.1

Best pass@1 per model · Higher is better

Not evaluated in DeepSWE 1.1

Arena Text

Best Arena rating per model · Higher is better

Arena #4

  1. 1522
    Gemini 4 ArgonNearby rank
  2. 1511
    Muse WonderSimilar price
  3. 1506
    Claude Opus 5.5
  4. 1504
    Claude Fable 5Nearby rank
  5. 1503
    Claude Opus 4.6Nearby rank
  6. 1490
    Claude Opus 5Predecessor
  7. 1487
    Gemini 3.1 Pro PreviewSimilar price
  8. 1354
    Command ASimilar price
  9. 1346
    GPT-4o (2024-05-13)Similar price

+16 vs Claude Opus 5 (predecessor) · Ahead of 3 of 4 similarly priced models

Arena WebDev

Best Arena rating per model · Higher is better

Arena #2

  1. 1836
    Claude Fable 5.2Nearby rank
  2. 1814
    Claude Opus 5.5
  3. 1773
    Claude Sonnet 5.5Nearby rank
  4. 1768
    Gemini 4 CarbonNearby rank
  5. 1691
    Claude Opus 5Predecessor
  6. 1658
    Kimi K3Similar price
  7. 1649
    Muse WonderSimilar price
  8. 1615
    GPT-5.6 SolSimilar price
  9. 1446
    Gemini 3.1 Pro PreviewSimilar price

+123 vs Claude Opus 5 (predecessor) · Ahead of 4 of 4 similarly priced models

Arena Vision

Best Arena rating per model · Higher is better

Arena #6

  1. 1299
    Qwen3.8 MaxNearby rank
  2. 1299
    Claude Opus 4.6Nearby rank
  3. 1295
    Claude Opus 5.5
  4. 1294
    Gemini 3.7 FlashNearby rank
  5. 1294
    Muse Spark 1.2Nearby rank
  6. 1288
    GPT-5.6 SolSimilar price
  7. 1285
    Claude Opus 5Predecessor
  8. 1285
    GPT-5.5Similar price
  9. 1280
    Gemini 3.1 Pro PreviewSimilar price
  10. 1162
    GPT-4o (2024-05-13)Similar price

Level with Claude Opus 5 (predecessor, overlapping 95% CIs) · Ahead of 2 of 4 similarly priced models

Arena Search

Best Arena rating per model · Higher is better

Arena #11

  1. 1255
    GPT-5.6 SolSimilar price
  2. 1248
    GPT-6.1 SolSimilar price
  3. 1229
    GPT-6 SolSimilar price
  4. 1227
    Claude Fable 5.1Nearby rank
  5. 1213
    Claude Opus 5Predecessor
  6. 1213
    Claude Opus 5.5
  7. 1211
    GPT-6 LunaNearby rank
  8. 1210
    Claude Opus 4.7Nearby rank
  9. 1142
    Sonar ProSimilar price

Level with Claude Opus 5 (predecessor) · Ahead of 1 of 4 similarly priced models

Arena Document

Best Arena rating per model · Higher is better

Not ranked on Arena Document yet

Agent Arena

Best IPS score per model · Higher is better

Arena #2

  1. +0.304
    Claude Fable 5.2Nearby rank
  2. +0.195
    Claude Opus 5.5
  3. +0.170
    Gemini 4 CarbonNearby rank
  4. +0.160
    Claude Sonnet 5.5Nearby rank
  5. +0.072
    Claude Opus 5Predecessor
  6. +0.046
    GPT-5.6 SolSimilar price
  7. +0.018
    Muse WonderSimilar price
  8. +0.006
    Kimi K3Similar price
  9. -0.045
    Gemini 3.1 Pro PreviewSimilar price

+0.123 vs Claude Opus 5 (predecessor) · Ahead of 4 of 4 similarly priced models

ARC-AGI-2

Best score per model · Higher is better

#5 of 85

  1. 94.2%
    GPT-6.1 SolNearby rank
  2. 93.8%
    Claude Fable 5.2Nearby rank
  3. 93.3%
    Claude Opus 5.5
  4. 92.5%
    GPT-5.6 SolSimilar price
  5. 91.3%
    Gemini 4 ArgonNearby rank
  6. 88.3%
    Claude Opus 5Predecessor
  7. 85.0%
    GPT-5.5Similar price
  8. 77.1%
    Gemini 3.1 Pro PreviewSimilar price
  9. 60.4%
    Kimi K3Similar price

+5.0 pts vs Claude Opus 5 (predecessor) · Ahead of 4 of 4 similarly priced models

FrontierMath-Tier-4-v2-Private

Best score per model · Higher is better

#5 of 72

  1. 97.6%
    GPT-6 AstraNearby rank
  2. 95.1%
    Gemini 4 CarbonNearby rank
  3. 95.0%
    Claude Opus 5.5
  4. 92.7%
    GPT-6.1 TerraNearby rank
  5. 90.2%
    Claude Fable 5Nearby rank
  6. 82.9%
    GPT-5.6 SolSimilar price
  7. 73.2%
    Claude Opus 5Predecessor
  8. 72.5%
    GPT-5.5Similar price
  9. 39.0%
    Kimi K3Similar price
  10. 26.8%
    Gemini 3.1 Pro PreviewSimilar price

+21.8 pts vs Claude Opus 5 (predecessor) · Ahead of 4 of 4 similarly priced models

FrontierMath-Tiers-1-3-v2-Private

Best score per model · Higher is better

#4 of 87

  1. 93.7%
    GPT-6 AstraNearby rank
  2. 93.7%
    GPT-6.1 SolNearby rank
  3. 91.2%
    Claude Opus 5.5
  4. 90.9%
    GPT-6.1 TerraNearby rank
  5. 90.5%
    Gemini 4 CarbonNearby rank
  6. 89.1%
    GPT-5.6 SolSimilar price
  7. 85.6%
    Claude Opus 5Predecessor
  8. 85.3%
    GPT-5.5Similar price
  9. 72.2%
    Kimi K3Similar price
  10. 59.6%
    Gemini 3.1 Pro PreviewSimilar price

+5.6 pts vs Claude Opus 5 (predecessor) · Ahead of 4 of 4 similarly priced models

GPQA diamond

Best score per model · Higher is better

#39 of 161

  1. 94.4%
    Gemini 3.1 Pro PreviewSimilar price
  2. 93.9%
    Claude Opus 5Predecessor
  3. 93.5%
    GPT-5.6 SolSimilar price
  4. 93.1%
    Kimi K3Similar price
  5. 90.8%
    Kimi K2.6Nearby rank
  6. 90.7%
    GPT-5.5Nearby rank
  7. 90.6%
    Claude Opus 5.5
  8. 90.5%
    Claude Opus 4.6Nearby rank
  9. 90.5%
    Claude Sonnet 5Nearby rank
  10. 48.9%
    GPT-4o (2024-05-13)Similar price

-3.3 pts vs Claude Opus 5 (predecessor) · Ahead of 1 of 4 similarly priced models

OTIS Mock AIME 2024-2025

Best score per model · Higher is better

#1 of 158

  1. 100.0%
    Claude Fable 5Nearby rank
  2. 100.0%
    Claude Fable 5.1Nearby rank
  3. 100.0%
    Claude Opus 5.5
  4. 100.0%
    Claude Sonnet 5.5Nearby rank
  5. 100.0%
    Gemini 4 ArgonNearby rank
  6. 100.0%
    GPT-5.6 SolSimilar price
  7. 98.9%
    Claude Opus 5Predecessor
  8. 97.2%
    Kimi K3Similar price
  9. 95.6%
    Gemini 3.1 Pro PreviewSimilar price
  10. 6.3%
    GPT-4o (2024-05-13)Similar price

+1.1 pts vs Claude Opus 5 (predecessor) · Ahead of 3 of 4 similarly priced models

SimpleQA Verified

Best score per model · Higher is better

#7 of 87

  1. 73.9%
    GPT-6.1 SolNearby rank
  2. 73.5%
    Gemini 3.1 Pro PreviewSimilar price
  3. 72.2%
    Claude Opus 5.5
  4. 70.8%
    Claude Fable 5.1Nearby rank
  5. 70.7%
    Claude Fable 5Nearby rank
  6. 69.7%
    GPT-5.6 SolSimilar price
  7. 63.0%
    GPT-5.5Similar price
  8. 59.9%
    Claude Opus 5Predecessor
  9. 50.6%
    Kimi K3Similar price

+12.3 pts vs Claude Opus 5 (predecessor) · Ahead of 3 of 4 similarly priced models

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Reasoning effort

ARC-AGI-2

Score by reasoning effort · Higher is better

All published scores

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.