Claude Opus 5.5
- Input
- $4.00/M tok
- Output
- $20/M tok
- Blended
- $8.00/M tok · 3:1
- Speed
- 92tok/s
- Context
- 1Mtokens
- Cost per task
- $10/task · AA
Speed measured on the xhigh effort variant.
Rankings
Coding
Mixed#2 / 137rank by quality94.3±3.6quality / 1005/7 benchmarks measuredPrice frontierSpeed frontierWriting & chat
Verified#5 / 162rank by quality89.0±4.3quality / 1003/5 benchmarks measuredSpeed frontierVision
Verified#3 / 98rank by quality93.1±4.8quality / 1003/6 benchmarks measuredPrice frontierSpeed frontierHard reasoning
Verified#3 / 218rank by quality92.8±5.1quality / 1002/4 benchmarks measuredSpeed frontierAgents
Verified#1 / 187rank by quality97.7±5.0quality / 1002/7 benchmarks measuredPrice frontierSpeed frontier
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#2 of 21 (estimated)~93.9%
No published score — estimated from related benchmarks
DeepSWE v1.1Verified
#15 of 4568.4%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #14GPT-6 Sol69.0%
- #15Claude Opus 5.568.4%
- #15Kimi K368.4%
artificialanalysis.ai · 2026-09-24
Terminal-Bench 4.0Verified
#3 of 10159.6%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #3Claude Fable 5.259.6%
- #3Claude Opus 5.559.6%
- #5GPT-6 Astra59.1%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#3 of 28 (estimated)~91.3%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- ~#3Claude Opus 5.5Estimated91.3%
- #3Qwen3.8 27B90.3%
No published score — estimated from related benchmarks
Writing & chat
#7 of 252050 Elo
eqbench.com · 2026-09-24
Vision
CharXiv ReasoningEstimated
~#2 of 12 (estimated)~86.1%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#2 of 8 (estimated)~91.4%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#6 of 4726.2%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #6Claude Fable 5.126.2%
- #6Claude Opus 5.526.2%
- #8GPT-6 Sol24.8%
artificialanalysis.ai · 2026-09-24
Hard reasoning
GPQA DiamondEstimated
~#2 of 193 (estimated)~96.1%
No published score — estimated from related benchmarks
AIME (latest)Estimated
~#2 of 34 (estimated)~99.2%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#2 of 120 (estimated)~98.3%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#2 of 15 (estimated)~84.5%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#2 of 5 (estimated)~58.6%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#2 of 22 (estimated)~92.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#3 of 91 (estimated)~50.0%
No published score — estimated from related benchmarks
Not comparable across labs (1)
Kept for reference, not counted in rankings: these use a lab-specific task set, answer key or scoring, so scores can't be compared fairly across labs. Only published scores are shown.