Skip to main content
BenchLM
Advertise

Model comparison

Claude Sonnet 4.6 vs GPT-5.5

Data verified

Head-to-head evidence from 27 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

65.07/100
Margin
8.4pts
winning →
GPT-5.5
OpenAI
73.51/100
3 category wins2 category wins

Public leaderboard positions: Claude Sonnet 4.6 #32 (Supported); GPT-5.5 #9 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Sonnet 4.6 and GPT-5.5 share 27 comparable benchmark results. 5 of 8 categories are comparable. 6 results are unique to Claude Sonnet 4.6; 30 to GPT-5.5.

Updated July 22, 2026
Shared results
27
Claude Sonnet 4.6 only
6
GPT-5.5 only
30
Comparable categories
5 / 8

Pick GPT-5.5 if you want the stronger benchmark profile. Claude Sonnet 4.6 only becomes the better choice if coding is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 27 shared benchmark results across 7 evidence categories; 5 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

GPT-5.5 is clearly ahead on the BenchAlign aggregate, 73.51 to 65.07. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.5's sharpest advantage is in mathematics, where it averages 47.6 against 26.4. The single biggest benchmark swing on the page is FrontierMath v2 (Tier 4), 8.300% to 35.400%. Claude Sonnet 4.6 does hit back in coding, so the answer changes if that is the part of the workload you care about most.

GPT-5.5 is also the more expensive model on tokens at $5.00 input / $30.00 output per 1M tokens, versus $3.00 input / $15.00 output per 1M tokens for Claude Sonnet 4.6. That is roughly 2.0x on output cost alone. GPT-5.5 is the reasoning model in the pair, while Claude Sonnet 4.6 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-5.5 gives you the larger context window at 1M, compared with 200K for Claude Sonnet 4.6.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Claude Sonnet 4.6 and GPT-5.5
CategoryClaude Sonnet 4.6ΔGPT-5.5
MathClaude Sonnet 4.626.4Margin→ 21.2GPT-5.547.6
AgenticClaude Sonnet 4.665.2Margin→ 16.4GPT-5.581.6
CodingClaude Sonnet 4.669.1Margin← 10.5GPT-5.558.6
KnowledgeClaude Sonnet 4.666.0Margin← 8.2GPT-5.557.8
MultimodalClaude Sonnet 4.677.4Margin← 7.0GPT-5.570.4
ReasoningClaude Sonnet 4.6Not measuredMarginNo overlapGPT-5.585.0

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Claude Sonnet 4.6B · GPT-5.5

  1. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 8.300%B 35.400%
    Winner: GPT-5.5Δ 27.1
    FrontierMath v2 (Tier 4): Claude Sonnet 4.6 scored 8.300%; GPT-5.5 scored 35.400%. GPT-5.5 wins this benchmark.

  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 59.1%B 82%
    Winner: GPT-5.5Δ 22.9
    Terminal-Bench 2.0: Claude Sonnet 4.6 scored 59.1%; GPT-5.5 scored 82%. GPT-5.5 wins this benchmark.

  3. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 32.400%B 51.700%
    Winner: GPT-5.5Δ 19.3
    FrontierMath v2 (Tiers 1-3): Claude Sonnet 4.6 scored 32.400%; GPT-5.5 scored 51.700%. GPT-5.5 wins this benchmark.

  4. OSWorld-Verified

    Agentic
    Source ↗
    A 72.1%B 78.7%
    Winner: GPT-5.5Δ 6.6
    OSWorld-Verified: Claude Sonnet 4.6 scored 72.1%; GPT-5.5 scored 78.7%. GPT-5.5 wins this benchmark.

  5. GPQA

    Knowledge
    Source ↗
    A 89.9%B 93.6%
    Winner: GPT-5.5Δ 3.7
    GPQA: Claude Sonnet 4.6 scored 89.9%; GPT-5.5 scored 93.6%. GPT-5.5 wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricClaude Sonnet 4.6GPT-5.5Comparison
Input / output priceUSD per 1M tokensClaude Sonnet 4.6$3 input / $15 outputGPT-5.5$5 input / $30 outputClaude Sonnet 4.6 has the lower combined listed price.
Generation speedtokens per secondClaude Sonnet 4.644 tok/sGPT-5.5Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Sonnet 4.61.48 sGPT-5.5Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Sonnet 4.6200KGPT-5.51MGPT-5.5 lists the larger context window.

Benchmark Deep Dive

AgenticGPT-5.5 wins
BenchmarkClaude Sonnet 4.6GPT-5.5Result
Terminal-Bench 2.0Source 59.1%82%GPT-5.5 leads
OSWorld-VerifiedSource 72.1%78.7%GPT-5.5 leads
Claw-EvalSource 67.8%—Not comparable
CyberGymSource 65.2%81.8%GPT-5.5 leads
τ²-bench resultsSource 79.5%93.9%GPT-5.5 leads
Gert LabsSource 62.92%72.93%GPT-5.5 leads
OSWorld 2.0Source 8.3%13.0%GPT-5.5 leads
JobBenchSource 36.9%42.7%GPT-5.5 leads
BrowseCompSource —84.4%Not comparable
MCP AtlasSource —75.3%Not comparable
ToolathlonSource —55.6%Not comparable
AA Agentic IndexSource —44.9%Not comparable
APEX-Agents-AASource —37.7%Not comparable
GDPval-AASource —49.5%Not comparable
GDPval-AASource —1490Not comparable
ResearchClawBenchSource —17.0%Not comparable
ExploitGymSource —13.4%Not comparable
AA BriefcaseSource —1154Not comparable
AA AutomationBenchSource —42.1%Not comparable
AA EnterpriseOps-GymSource —46.6%Not comparable
AA Harvey LABSource —86.3%Not comparable
AA ITBenchSource —45.8%Not comparable
AA Tau3 BankingSource —31.3%Not comparable
terminalBenchHardSource —60.6%Not comparable
aaTerminalBench21Source —84.3%Not comparable
CodingClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6GPT-5.5Result
SWE-bench VerifiedSource 79.6%—Not comparable
SWE-RebenchSource 60.7%—Not comparable
React Native EvalsSource 80.6%84.7%GPT-5.5 leads
Vibe Code BenchSource 51.48%69.85%GPT-5.5 leads
cursorBench31Source 48.8%59.2%GPT-5.5 leads
AA-SciCodeSource 46.9%56.1%GPT-5.5 leads
FrontierCode 1.1 MainSource 24.3%43.0%GPT-5.5 leads
SWE-bench ProSource —58.6%Not comparable
Terminal-Bench 2.0Source —82.0%Not comparable
cursorBench32Source —58.4%Not comparable
AA Coding IndexSource —74.9%Not comparable
Reasoning
BenchmarkClaude Sonnet 4.6GPT-5.5Result
AA-LCRSource 57.7%74.3%GPT-5.5 leads
CritPtSource 0.9%27.1%GPT-5.5 leads
MRCR v2 64K-128KSource —83.1%Not comparable
MRCR v2 128K-256KSource —87.5%Not comparable
ARC-AGI-2Source —85%Not comparable
KnowledgeClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6GPT-5.5Result
GPQASource 89.9%93.6%GPT-5.5 leads
SuperGPQASource 95%—Not comparable
MMLU-ProSource 79.2%—Not comparable
HLESource 49%52.2%GPT-5.5 leads
Artificial Analysis Intelligence IndexSource 35.9%54.8%GPT-5.5 leads
AA-GPQA DiamondSource 79.9%93.5%GPT-5.5 leads
AA-HLESource 13.2%44.3%GPT-5.5 leads
AA-Omniscience IndexSource -2.9%20.1%GPT-5.5 leads
AA-Omniscience AccuracySource 38.0%56.9%GPT-5.5 leads
AA-Omniscience Hallucination RateSource 65.9%85.5%Claude Sonnet 4.6 leads
GPQA-DSource —93.6%Not comparable
HLE w/o toolsSource —41.4%Not comparable
MathGPT-5.5 wins
BenchmarkClaude Sonnet 4.6GPT-5.5Result
FrontierMath v2 (Tiers 1-3)Source 32.400%51.700%GPT-5.5 leads
FrontierMath v2 (Tier 4)Source 8.300%35.400%GPT-5.5 leads
FrontierMath (legacy)Source —51.7%Not comparable
MultimodalClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6GPT-5.5Result
CharXivSource 77.4%—Not comparable
AA-MMMU-ProSource 70.6%79.9%GPT-5.5 leads
Design Arena WebsiteSource 13141282Claude Sonnet 4.6 leads
MMMU-ProSource —81.2%Not comparable
MMMU-Pro w/ PythonSource —83.2%Not comparable
OfficeQA ProSource —54.1%Not comparable
Inst. Following
BenchmarkClaude Sonnet 4.6GPT-5.5Result
AA-IFBenchSource 41.2%75.9%GPT-5.5 leads
Frequently Asked Questions (6)

Which is better, Claude Sonnet 4.6 or GPT-5.5?

GPT-5.5 is ahead on BenchLM's BenchAlign leaderboard, 73.51 to 65.07. The biggest single separator in this matchup is FrontierMath v2 (Tier 4), where the scores are 8.300% and 35.400%.

Which is better for knowledge tasks, Claude Sonnet 4.6 or GPT-5.5?

Claude Sonnet 4.6 has the edge for knowledge tasks in this comparison, averaging 66 versus 57.8. Inside this category, AA-HLE is the benchmark that creates the most daylight between them.

Which is better for coding, Claude Sonnet 4.6 or GPT-5.5?

Claude Sonnet 4.6 has the edge for coding in this comparison, averaging 69.1 versus 58.6. Inside this category, FrontierCode 1.1 Main is the benchmark that creates the most daylight between them.

Which is better for math, Claude Sonnet 4.6 or GPT-5.5?

GPT-5.5 has the edge for math in this comparison, averaging 47.6 versus 26.4. Inside this category, FrontierMath v2 (Tier 4) is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Sonnet 4.6 or GPT-5.5?

GPT-5.5 has the edge for agentic tasks in this comparison, averaging 81.6 versus 65.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Claude Sonnet 4.6 or GPT-5.5?

Claude Sonnet 4.6 has the edge for multimodal and grounded tasks in this comparison, averaging 77.4 versus 70.4. Inside this category, Design Arena Website is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Anthropic Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 22, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.