Skip to main content
BenchLM
Advertise

Model comparison

Claude Sonnet 4.6 vs Claude Sonnet 5

Data verified

Head-to-head evidence from 17 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

65.07/100
Margin
0.3pts
winning →
65.32/100
1 category wins3 category wins

Public leaderboard positions: Claude Sonnet 4.6 #32 (Supported); Claude Sonnet 5 #29 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Sonnet 4.6 and Claude Sonnet 5 share 17 comparable benchmark results. 4 of 8 categories are comparable. 16 results are unique to Claude Sonnet 4.6; 19 to Claude Sonnet 5.

Updated July 23, 2026
Shared results
17
Claude Sonnet 4.6 only
16
Claude Sonnet 5 only
19
Comparable categories
4 / 8

Pick Claude Sonnet 5 if you want the stronger benchmark profile. Claude Sonnet 4.6 only becomes the better choice if knowledge is the priority or you would rather avoid the extra latency and token burn of a reasoning model.

Confidence note. This is a partial-evidence comparison with 17 shared benchmark results across 5 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Claude Sonnet 5 has the cleaner BenchAlign overall profile here, landing at 65.32 versus 65.07. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Claude Sonnet 5's sharpest advantage is in agentic, where it averages 81.9 against 65.2. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 59.1% to 80.4%. Claude Sonnet 4.6 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

Claude Sonnet 4.6 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $2.00 input / $10.00 output per 1M tokens for Claude Sonnet 5. Claude Sonnet 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. Claude Sonnet 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 Claude Sonnet 5
CategoryClaude Sonnet 4.6ΔClaude Sonnet 5
AgenticClaude Sonnet 4.665.2Margin→ 16.7Claude Sonnet 581.9
MultimodalClaude Sonnet 4.677.4Margin→ 10.9Claude Sonnet 588.3
KnowledgeClaude Sonnet 4.666.0Margin← 8.6Claude Sonnet 557.4
CodingClaude Sonnet 4.669.1Margin→ 7.6Claude Sonnet 576.7
MathClaude Sonnet 4.626.4MarginNo overlapClaude Sonnet 5Not measured

Decisive benchmark drivers

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

More
A · Claude Sonnet 4.6B · Claude Sonnet 5

  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 59.1%B 80.4%
    Winner: Claude Sonnet 5Δ 21.3
    Terminal-Bench 2.0: Claude Sonnet 4.6 scored 59.1%; Claude Sonnet 5 scored 80.4%. Claude Sonnet 5 wins this benchmark.

  2. CharXiv

    Multimodal
    Source ↗
    A 77.4%B 88.3%
    Winner: Claude Sonnet 5Δ 10.9
    CharXiv: Claude Sonnet 4.6 scored 77.4%; Claude Sonnet 5 scored 88.3%. Claude Sonnet 5 wins this benchmark.

  3. OSWorld-Verified

    Agentic
    Source ↗
    A 72.1%B 81.2%
    Winner: Claude Sonnet 5Δ 9.1
    OSWorld-Verified: Claude Sonnet 4.6 scored 72.1%; Claude Sonnet 5 scored 81.2%. Claude Sonnet 5 wins this benchmark.

  4. HLE

    Knowledge
    Source ↗
    A 49%B 57.4%
    Winner: Claude Sonnet 5Δ 8.4
    HLE: Claude Sonnet 4.6 scored 49%; Claude Sonnet 5 scored 57.4%. Claude Sonnet 5 wins this benchmark.

  5. SWE-bench Verified

    Coding
    Source ↗
    A 79.6%B 85.2%
    Winner: Claude Sonnet 5Δ 5.6
    SWE-bench Verified: Claude Sonnet 4.6 scored 79.6%; Claude Sonnet 5 scored 85.2%. Claude Sonnet 5 wins this benchmark.

Operational comparison

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

MetricClaude Sonnet 4.6Claude Sonnet 5Comparison
Input / output priceUSD per 1M tokensClaude Sonnet 4.6$3 input / $15 outputClaude Sonnet 5$2 input / $10 outputClaude Sonnet 5 has the lower combined listed price.
Generation speedtokens per secondClaude Sonnet 4.644 tok/sClaude Sonnet 5Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Sonnet 4.61.48 sClaude Sonnet 5Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Sonnet 4.6200KClaude Sonnet 51MClaude Sonnet 5 lists the larger context window.

Benchmark Deep Dive

AgenticClaude Sonnet 5 wins
BenchmarkClaude Sonnet 4.6Claude Sonnet 5Result
Terminal-Bench 2.0Source 59.1%80.4%Claude Sonnet 5 leads
OSWorld-VerifiedSource 72.1%81.2%Claude Sonnet 5 leads
Claw-EvalSource 67.8%—Not comparable
CyberGymSource 65.2%—Not comparable
τ²-bench resultsSource 79.5%—Not comparable
Gert LabsSource 62.92%—Not comparable
OSWorld 2.0Source 8.3%—Not comparable
JobBenchSource 36.9%—Not comparable
BrowseCompSource —84.7%Not comparable
HLE w/ toolsSource —57.4%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
CodingClaude Sonnet 5 wins
BenchmarkClaude Sonnet 4.6Claude Sonnet 5Result
SWE-bench VerifiedSource 79.6%85.2%Claude Sonnet 5 leads
SWE-RebenchSource 60.7%—Not comparable
React Native EvalsSource 80.6%—Not comparable
Vibe Code BenchSource 51.48%—Not comparable
cursorBench31Source 48.8%—Not comparable
AA-SciCodeSource 46.9%53.6%Claude Sonnet 5 leads
FrontierCode 1.1 MainSource 24.3%42.7%Claude Sonnet 5 leads
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
cursorBench32Source —61.5%Not comparable
AA Coding IndexSource —71.5%Not comparable
Reasoning
BenchmarkClaude Sonnet 4.6Claude Sonnet 5Result
AA-LCRSource 57.7%70.7%Claude Sonnet 5 leads
CritPtSource 0.9%16.9%Claude Sonnet 5 leads
KnowledgeClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6Claude Sonnet 5Result
GPQASource 89.9%—Not comparable
SuperGPQASource 95%—Not comparable
MMLU-ProSource 79.2%—Not comparable
HLESource 49%57.4%Claude Sonnet 5 leads
Artificial Analysis Intelligence IndexSource 35.9%53.4%Claude Sonnet 5 leads
AA-GPQA DiamondSource 79.9%91.1%Claude Sonnet 5 leads
AA-HLESource 13.2%39.6%Claude Sonnet 5 leads
AA-Omniscience IndexSource -2.9%15.3%Claude Sonnet 5 leads
AA-Omniscience AccuracySource 38.0%38.3%Claude Sonnet 5 leads
AA-Omniscience Hallucination RateSource 65.9%37.3%Claude Sonnet 5 leads
HLE w/o toolsSource —43.2%Not comparable
Math
BenchmarkClaude Sonnet 4.6Claude Sonnet 5Result
FrontierMath v2 (Tiers 1-3)Source 32.400%—Not comparable
FrontierMath v2 (Tier 4)Source 8.300%—Not comparable
MultimodalClaude Sonnet 5 wins
BenchmarkClaude Sonnet 4.6Claude Sonnet 5Result
CharXivSource 77.4%88.3%Claude Sonnet 5 leads
AA-MMMU-ProSource 70.6%77.3%Claude Sonnet 5 leads
Design Arena WebsiteSource 13141314Tie
CharXiv w/o toolsSource —77%Not comparable
Inst. Following
BenchmarkClaude Sonnet 4.6Claude Sonnet 5Result
AA-IFBenchSource 41.2%—Not comparable
Frequently Asked Questions (5)

Which is better, Claude Sonnet 4.6 or Claude Sonnet 5?

Claude Sonnet 5 is ahead on BenchLM's BenchAlign leaderboard, 65.32 to 65.07. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 59.1% and 80.4%.

Which is better for knowledge tasks, Claude Sonnet 4.6 or Claude Sonnet 5?

Claude Sonnet 4.6 has the edge for knowledge tasks in this comparison, averaging 66 versus 57.4. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.

Which is better for coding, Claude Sonnet 4.6 or Claude Sonnet 5?

Claude Sonnet 5 has the edge for coding in this comparison, averaging 76.7 versus 69.1. Inside this category, FrontierCode 1.1 Main is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Sonnet 4.6 or Claude Sonnet 5?

Claude Sonnet 5 has the edge for agentic tasks in this comparison, averaging 81.9 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 Claude Sonnet 5?

Claude Sonnet 5 has the edge for multimodal and grounded tasks in this comparison, averaging 88.3 versus 77.4. Inside this category, CharXiv 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 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.