Compare · ModelsLive · 2 picked · head to head
Claude Sonnet 5.5 vs Claude Opus 5
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Sonnet 5.5 wins on 9/11 benchmarks
Claude Sonnet 5.5 wins 9 of 11 shared benchmarks. Leads in agentic · math · general.
Category leads
agentic·Claude Sonnet 5.5coding·Claude Opus 5math·Claude Sonnet 5.5general·Claude Sonnet 5.5knowledge·Claude Sonnet 5.5
Hype vs Reality
Attention vs performance
Claude Sonnet 5.5
#11 by perf·#10 by attention
Claude Opus 5
#21 by perf·#6 by attention
Best value
Claude Sonnet 5.5
2.7x better value than Claude Opus 5
Claude Sonnet 5.5
12.5 pts/$
$6.00/M
Claude Opus 5
4.6 pts/$
$15.00/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
Anthropic
$965.0B·Tier 1
Head to head
11 benchmarks · 2 models
Claude Sonnet 5.5Claude Opus 5
APEX-Agents
Claude Sonnet 5.5 leads by +9.7
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Claude Sonnet 5.5
75.5
Claude Opus 5
65.8
Frontiercode
Claude Opus 5 leads by +1.3
Claude Sonnet 5.5
52.1
Claude Opus 5
53.4
FrontierMath-Tier-4-v2-Private
Claude Sonnet 5.5 leads by +7.3
Claude Sonnet 5.5
80.5
Claude Opus 5
73.2
FrontierMath-Tiers-1-3-v2-Private
Claude Sonnet 5.5 leads by +3.2
Claude Sonnet 5.5
88.8
Claude Opus 5
85.6
Frontierswe
Claude Sonnet 5.5 leads by +9.9
Claude Sonnet 5.5
61.9
Claude Opus 5
52.0
Furniture Assembly
Claude Sonnet 5.5 leads by +20.2
Claude Sonnet 5.5
64.3
Claude Opus 5
44.0
GPQA diamond
Claude Sonnet 5.5 leads by +2.3
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Sonnet 5.5
94.1
Claude Opus 5
91.8
Mystery Game Puzzles
Claude Sonnet 5.5 leads by +6.6
Claude Sonnet 5.5
61.5
Claude Opus 5
54.8
OTIS Mock AIME 2024-2025
Claude Sonnet 5.5 leads by +1.1
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Sonnet 5.5
100.0
Claude Opus 5
98.9
Proofbench
Claude Sonnet 5.5 leads by +1.0
Claude Sonnet 5.5
100.0
Claude Opus 5
99.0
SimpleQA Verified
Claude Opus 5 leads by +13.4
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Sonnet 5.5
46.5
Claude Opus 5
59.9
Full benchmark table
| Benchmark | Claude Sonnet 5.5 | Claude Opus 5 |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 75.5 | 65.8 |
Frontiercode | 52.1 | 53.4 |
FrontierMath-Tier-4-v2-Private | 80.5 | 73.2 |
FrontierMath-Tiers-1-3-v2-Private | 88.8 | 85.6 |
Frontierswe | 61.9 | 52.0 |
Furniture Assembly | 64.3 | 44.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 94.1 | 91.8 |
Mystery Game Puzzles | 61.5 | 54.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 100.0 | 98.9 |
Proofbench | 100.0 | 99.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 46.5 | 59.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $2.00 | $10.00 | 1.0M tokens (~500 books) | $40.00 | |
| $5.00 | $25.00 | 1.0M tokens (~500 books) | $100.00 |