Compare · ModelsLive · 2 picked · head to head
Claude Sonnet 5.5 vs GPT-5.5 Pro
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Sonnet 5.5 wins on 8/12 benchmarks
Claude Sonnet 5.5 wins 8 of 12 shared benchmarks. Leads in speed · general · math.
Category leads
speed·Claude Sonnet 5.5reasoning·GPT-5.5 Proknowledge·GPT-5.5 Progeneral·Claude Sonnet 5.5math·Claude Sonnet 5.5
Head to head · from the data · data as of 2026-11-17
- Benchmarks · Claude Sonnet 5.5 leads on 6 of 12 shared benchmarks (Artificial Analysis · CritPt, Dtbench, FrontierMath-Tier-4-v2-Private, FrontierMath-Tiers-1-3-v2-Private, 2 more), GPT-5.5 Pro on 4 (ARC-AGI-2, Chess Puzzles, SimpleBench, SimpleQA Verified) · 2 tied
- Price · Claude Sonnet 5.5 input $2.00/M vs GPT-5.5 Pro $30.00/M, Claude Sonnet 5.5 is 93% cheaper (OpenRouter list price, as of 2026-11-17)
- Cheapest provider · Claude Sonnet 5.5 at Amazon Bedrock and 4 other providers $2.00/M input (of 10 offers) as of 2026-11-17 · GPT-5.5 Pro at OpenAI $30.00/M input (1 offer) as of 2026-11-17
- Context · Claude Sonnet 5.5 1.0M tokens vs GPT-5.5 Pro 1.1M tokens
- Released · Claude Sonnet 5.5 Sep 28, 2026 vs GPT-5.5 Pro Apr 24, 2026 · 5 months apart
- Price history · Claude Sonnet 5.5 OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-17 · GPT-5.5 Pro OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-17
Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.
Hype vs Reality
Attention vs performance
Claude Sonnet 5.5
#18 by perf·#12 by attention
GPT-5.5 Pro
#8 by perf·#11 by attention
Best value
Claude Sonnet 5.5
16.4x better value than GPT-5.5 Pro
Claude Sonnet 5.5
11.9 pts/$
$6.00/M
GPT-5.5 Pro
0.7 pts/$
$105.00/M
Vendor risk
Who is behind the model
Anthropic
$1.40T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
12 benchmarks · 2 models
Claude Sonnet 5.5GPT-5.5 Pro
Artificial Analysis · CritPt
Claude Sonnet 5.5 leads by +0.8
Claude Sonnet 5.5
31.4
GPT-5.5 Pro
30.6
ARC-AGI
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude Sonnet 5.5
96.5
GPT-5.5 Pro
96.5
ARC-AGI-2
GPT-5.5 Pro leads by +0.7
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Claude Sonnet 5.5
83.9
GPT-5.5 Pro
84.6
Chess Puzzles
GPT-5.5 Pro leads by +3.2
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Sonnet 5.5
56.9
GPT-5.5 Pro
60.0
Dtbench
Claude Sonnet 5.5 leads by +2.2
Claude Sonnet 5.5
95.5
GPT-5.5 Pro
93.3
FrontierMath-Tier-4-v2-Private
Claude Sonnet 5.5 leads by +2.4
Claude Sonnet 5.5
80.5
GPT-5.5 Pro
78.0
FrontierMath-Tiers-1-3-v2-Private
Claude Sonnet 5.5 leads by +1.1
Claude Sonnet 5.5
93.4
GPT-5.5 Pro
92.3
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
98.0
GPT-5.5 Pro
95.7
Lmca
Claude Sonnet 5.5 leads by +16.9
Claude Sonnet 5.5
80.3
GPT-5.5 Pro
63.5
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Sonnet 5.5
100.0
GPT-5.5 Pro
100.0
SimpleBench
GPT-5.5 Pro leads by +1.2
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Claude Sonnet 5.5
71.1
GPT-5.5 Pro
72.3
SimpleQA Verified
GPT-5.5 Pro leads by +18.0
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
GPT-5.5 Pro
64.5
Full benchmark table
| Benchmark | Claude Sonnet 5.5 | GPT-5.5 Pro |
|---|---|---|
Artificial Analysis · CritPt | 31.4 | 30.6 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 96.5 | 96.5 |
ARC-AGI-2 ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data. | 83.9 | 84.6 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 56.9 | 60.0 |
Dtbench | 95.5 | 93.3 |
FrontierMath-Tier-4-v2-Private | 80.5 | 78.0 |
FrontierMath-Tiers-1-3-v2-Private | 93.4 | 92.3 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 98.0 | 95.7 |
Lmca | 80.3 | 63.5 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 100.0 | 100.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 71.1 | 72.3 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 46.5 | 64.5 |
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 | |
| $30.00 | $180.00 | 1.1M tokens (~525 books) | $675.00 |
Claude Sonnet 5.5 vs GPT-5.5 Pro · questions answered from the data
Claude Sonnet 5.5 leads on 6 of 12 shared benchmarks (Artificial Analysis · CritPt, Dtbench, FrontierMath-Tier-4-v2-Private, FrontierMath-Tiers-1-3-v2-Private, 2 more), GPT-5.5 Pro on 4 (ARC-AGI-2, Chess Puzzles, SimpleBench, SimpleQA Verified) · 2 tied