Skip to main content
BenchLM
Advertise

Model comparison

Claude 3.5 Sonnet vs Claude Sonnet 4.6

Data verified

Head-to-head evidence from 4 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

47.74/100
Margin
17.3pts
winning →
65.07/100
0 category wins3 category wins

Public leaderboard positions: Claude 3.5 Sonnet #132 (Estimated); Claude Sonnet 4.6 #32 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude 3.5 Sonnet and Claude Sonnet 4.6 share 4 comparable benchmark results. 3 of 8 categories are comparable. 0 results are unique to Claude 3.5 Sonnet; 29 to Claude Sonnet 4.6.

Updated July 20, 2026
Shared results
4
Claude 3.5 Sonnet only
0
Claude Sonnet 4.6 only
29
Comparable categories
3 / 8

Pick Claude Sonnet 4.6 if you want the stronger benchmark profile. Claude 3.5 Sonnet only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 3 evidence categories; 3 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 4.6 is clearly ahead on the BenchAlign aggregate, 65.07 to 47.74. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Claude Sonnet 4.6's sharpest advantage is in mathematics, where it averages 26.4 against 1.6. The single biggest benchmark swing on the page is SWE-bench Verified, 49% to 79.6%.

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 3.5 Sonnet and Claude Sonnet 4.6
CategoryClaude 3.5 SonnetΔClaude Sonnet 4.6
MathClaude 3.5 Sonnet1.6Margin→ 24.8Claude Sonnet 4.626.4
CodingClaude 3.5 Sonnet49.0Margin→ 20.1Claude Sonnet 4.669.1
KnowledgeClaude 3.5 Sonnet59.4Margin→ 6.6Claude Sonnet 4.666.0
AgenticClaude 3.5 SonnetNot measuredMarginNo overlapClaude Sonnet 4.665.2
MultimodalClaude 3.5 SonnetNot measuredMarginNo overlapClaude Sonnet 4.677.4

Decisive benchmark drivers

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

More
A · Claude 3.5 SonnetB · Claude Sonnet 4.6

  1. SWE-bench Verified

    Coding
    Source ↗
    A 49%B 79.6%
    Winner: Claude Sonnet 4.6Δ 30.6
    SWE-bench Verified: Claude 3.5 Sonnet scored 49%; Claude Sonnet 4.6 scored 79.6%. Claude Sonnet 4.6 wins this benchmark.

  2. GPQA

    Knowledge
    Source ↗
    A 59.4%B 89.9%
    Winner: Claude Sonnet 4.6Δ 30.5
    GPQA: Claude 3.5 Sonnet scored 59.4%; Claude Sonnet 4.6 scored 89.9%. Claude Sonnet 4.6 wins this benchmark.

  3. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 2.069%B 32.400%
    Winner: Claude Sonnet 4.6Δ 30.3
    FrontierMath v2 (Tiers 1-3): Claude 3.5 Sonnet scored 2.069%; Claude Sonnet 4.6 scored 32.400%. Claude Sonnet 4.6 wins this benchmark.

  4. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 0.000%B 8.300%
    Winner: Claude Sonnet 4.6Δ 8.3
    FrontierMath v2 (Tier 4): Claude 3.5 Sonnet scored 0.000%; Claude Sonnet 4.6 scored 8.300%. Claude Sonnet 4.6 wins this benchmark.

Operational comparison

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

MetricClaude 3.5 SonnetClaude Sonnet 4.6Comparison
Input / output priceUSD per 1M tokensClaude 3.5 Sonnet$3 input / $15 outputClaude Sonnet 4.6$3 input / $15 outputListed prices are equal.
Generation speedtokens per secondClaude 3.5 SonnetNot availableClaude Sonnet 4.644 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude 3.5 SonnetNot availableClaude Sonnet 4.61.48 sA complete latency comparison is not available.
Context windowmaximum listed tokensClaude 3.5 Sonnet200KClaude Sonnet 4.6200KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkClaude 3.5 SonnetClaude Sonnet 4.6Result
Terminal-Bench 2.0Source —59.1%Not comparable
OSWorld-VerifiedSource —72.1%Not comparable
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
CodingClaude Sonnet 4.6 wins
BenchmarkClaude 3.5 SonnetClaude Sonnet 4.6Result
SWE-bench VerifiedSource 49%79.6%Claude Sonnet 4.6 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%Not comparable
FrontierCode 1.1 MainSource —24.3%Not comparable
Reasoning
BenchmarkClaude 3.5 SonnetClaude Sonnet 4.6Result
AA-LCRSource —57.7%Not comparable
CritPtSource —0.9%Not comparable
KnowledgeClaude Sonnet 4.6 wins
BenchmarkClaude 3.5 SonnetClaude Sonnet 4.6Result
GPQASource 59.4%89.9%Claude Sonnet 4.6 leads
SuperGPQASource —95%Not comparable
MMLU-ProSource —79.2%Not comparable
HLESource —49%Not comparable
Artificial Analysis Intelligence IndexSource —35.9%Not comparable
AA-GPQA DiamondSource —79.9%Not comparable
AA-HLESource —13.2%Not comparable
AA-Omniscience IndexSource —-2.9%Not comparable
AA-Omniscience AccuracySource —38.0%Not comparable
AA-Omniscience Hallucination RateSource —65.9%Not comparable
MathClaude Sonnet 4.6 wins
BenchmarkClaude 3.5 SonnetClaude Sonnet 4.6Result
FrontierMath v2 (Tiers 1-3)Source 2.069%32.400%Claude Sonnet 4.6 leads
FrontierMath v2 (Tier 4)Source 0.000%8.300%Claude Sonnet 4.6 leads
Multimodal
BenchmarkClaude 3.5 SonnetClaude Sonnet 4.6Result
CharXivSource —77.4%Not comparable
AA-MMMU-ProSource —70.6%Not comparable
Design Arena WebsiteSource —1317Not comparable
Inst. Following
BenchmarkClaude 3.5 SonnetClaude Sonnet 4.6Result
AA-IFBenchSource —41.2%Not comparable
Frequently Asked Questions (4)

Which is better, Claude 3.5 Sonnet or Claude Sonnet 4.6?

Claude Sonnet 4.6 is ahead on BenchLM's BenchAlign leaderboard, 65.07 to 47.74. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 49% and 79.6%.

Which is better for knowledge tasks, Claude 3.5 Sonnet or Claude Sonnet 4.6?

Claude Sonnet 4.6 has the edge for knowledge tasks in this comparison, averaging 66 versus 59.4. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for coding, Claude 3.5 Sonnet or Claude Sonnet 4.6?

Claude Sonnet 4.6 has the edge for coding in this comparison, averaging 69.1 versus 49. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, Claude 3.5 Sonnet or Claude Sonnet 4.6?

Claude Sonnet 4.6 has the edge for math in this comparison, averaging 26.4 versus 1.6. Inside this category, FrontierMath v2 (Tiers 1-3) 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 20, 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.