Skip to main content

Model comparison

Claude Opus 4.6 (Adaptive) vs Claude Sonnet 5

Data verified

Head-to-head evidence from 11 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

64.18/100
Margin
1.1pts
winning →
65.32/100
0 category wins0 category wins

Public leaderboard positions: Claude Opus 4.6 (Adaptive) #35 (Estimated); Claude Sonnet 5 #29 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Opus 4.6 (Adaptive) and Claude Sonnet 5 share 11 comparable benchmark results. 0 of 8 categories are comparable. 5 results are unique to Claude Opus 4.6 (Adaptive); 25 to Claude Sonnet 5.

Updated July 23, 2026
Shared results
11
Claude Opus 4.6 (Adaptive) only
5
Claude Sonnet 5 only
25
Comparable categories
0 / 8

Benchmark data for Claude Opus 4.6 (Adaptive) and Claude Sonnet 5 is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 4 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

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 Opus 4.6 (Adaptive) and Claude Sonnet 5
CategoryClaude Opus 4.6 (Adaptive)ΔClaude Sonnet 5
AgenticClaude Opus 4.6 (Adaptive)Not measuredMarginNo overlapClaude Sonnet 581.9
CodingClaude Opus 4.6 (Adaptive)Not measuredMarginNo overlapClaude Sonnet 576.7
KnowledgeClaude Opus 4.6 (Adaptive)Not measuredMarginNo overlapClaude Sonnet 557.4
MultimodalClaude Opus 4.6 (Adaptive)Not measuredMarginNo overlapClaude Sonnet 588.3

Operational comparison

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

MetricClaude Opus 4.6 (Adaptive)Claude Sonnet 5Comparison
Input / output priceUSD per 1M tokensClaude Opus 4.6 (Adaptive)Not availableClaude Sonnet 5$2 input / $10 outputA complete price comparison is not available.
Generation speedtokens per secondClaude Opus 4.6 (Adaptive)Not availableClaude Sonnet 5Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Opus 4.6 (Adaptive)Not availableClaude Sonnet 5Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Opus 4.6 (Adaptive)1MClaude Sonnet 51MListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkClaude Opus 4.6 (Adaptive)Claude Sonnet 5Result
APEX-Agents-AASource 33.0%Not comparable
τ²-bench resultsSource 92.1%Not comparable
Terminal-Bench 2.0Source 80.4%Not comparable
BrowseCompSource 84.7%Not comparable
HLE w/ toolsSource 57.4%Not comparable
OSWorld-VerifiedSource 81.2%Not comparable
GDPval-AASource 1607Not comparable
AA Agentic IndexSource 46.7%Not comparable
GDPval-AASource 55.4%Not comparable
AA BriefcaseSource 1388Not comparable
AA AutomationBenchSource 39.2%Not comparable
AA EnterpriseOps-GymSource 44.7%Not comparable
AA Harvey LABSource 90.1%Not comparable
AA Tau3 BankingSource 28.2%Not comparable
aaTerminalBench21Source 80.5%Not comparable
Coding
BenchmarkClaude Opus 4.6 (Adaptive)Claude Sonnet 5Result
Vibe Code BenchSource 53.50%Not comparable
AA-SciCodeSource 51.9%53.6%Claude Sonnet 5 leads
SWE-bench VerifiedSource 85.2%Not comparable
SWE-bench ProSource 63.2%Not comparable
SWE MultilingualSource 78.3%Not comparable
SWE MultimodalSource 28.1%Not comparable
Terminal-Bench 2.0Source 80.4%Not comparable
FrontierCode 1.1 MainSource 42.7%Not comparable
cursorBench32Source 61.5%Not comparable
AA Coding IndexSource 71.5%Not comparable
Reasoning
BenchmarkClaude Opus 4.6 (Adaptive)Claude Sonnet 5Result
AA-LCRSource 70.7%70.7%Tie
CritPtSource 12.6%16.9%Claude Sonnet 5 leads
Knowledge
BenchmarkClaude Opus 4.6 (Adaptive)Claude Sonnet 5Result
Artificial Analysis Intelligence IndexSource 43.7%53.4%Claude Sonnet 5 leads
AA-GPQA DiamondSource 89.6%91.1%Claude Sonnet 5 leads
AA-HLESource 36.7%39.6%Claude Sonnet 5 leads
AA-Omniscience IndexSource 13.5%15.3%Claude Sonnet 5 leads
AA-Omniscience AccuracySource 46.4%38.3%Claude Opus 4.6 (Adaptive) leads
AA-Omniscience Hallucination RateSource 61.3%37.3%Claude Sonnet 5 leads
HLESource 57.4%Not comparable
HLE w/o toolsSource 43.2%Not comparable
Multilingual
BenchmarkClaude Opus 4.6 (Adaptive)Claude Sonnet 5Result
AA Global-MMLU-LiteSource 92.2%Not comparable
Multimodal
BenchmarkClaude Opus 4.6 (Adaptive)Claude Sonnet 5Result
AA-MMMU-ProSource 75.4%77.3%Claude Sonnet 5 leads
Design Arena WebsiteSource 13251314Claude Opus 4.6 (Adaptive) leads
CharXivSource 88.3%Not comparable
CharXiv w/o toolsSource 77%Not comparable
Inst. Following
BenchmarkClaude Opus 4.6 (Adaptive)Claude Sonnet 5Result
AA-IFBenchSource 53.1%Not comparable
Frequently Asked Questions (3)

Can I compare Claude Opus 4.6 (Adaptive) and Claude Sonnet 5 on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for Claude Opus 4.6 (Adaptive) and Claude Sonnet 5 today?

Claude Sonnet 5: $2.00 input / $10.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Related Comparisons

Last updated: July 23, 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.