Skip to main content

Model comparison

Claude 3.5 Sonnet vs Claude 4 Sonnet

Data verified

Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.

47.74/100
Margin
5.0pts
← winning
42.79/100
0 category wins1 category wins

Public leaderboard positions: Claude 3.5 Sonnet #132 (Estimated); Claude 4 Sonnet #158 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude 3.5 Sonnet and Claude 4 Sonnet share 1 comparable benchmark result. 1 of 8 categories are comparable. 3 results are unique to Claude 3.5 Sonnet; 15 to Claude 4 Sonnet.

Updated July 22, 2026
Shared results
1
Claude 3.5 Sonnet only
3
Claude 4 Sonnet only
15
Comparable categories
1 / 8

Pick Claude 3.5 Sonnet if you want the stronger benchmark profile. Claude 4 Sonnet only becomes the better choice if coding is the priority.

Confidence note. This is a partial-evidence comparison with 1 shared benchmark result across 1 evidence category; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Claude 3.5 Sonnet is clearly ahead on the BenchAlign aggregate, 47.74 to 42.79. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

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 4 Sonnet
CategoryClaude 3.5 SonnetΔClaude 4 Sonnet
CodingClaude 3.5 Sonnet49.0Margin 23.7Claude 4 Sonnet72.7
KnowledgeClaude 3.5 Sonnet59.4MarginNo overlapClaude 4 SonnetNot measured
MathClaude 3.5 Sonnet1.6MarginNo overlapClaude 4 SonnetNot measured

Decisive benchmark drivers

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

More
A · Claude 3.5 SonnetB · Claude 4 Sonnet
  1. SWE-bench Verified

    Coding
    Source ↗
    A 49%B 72.7%
    Winner: Claude 4 SonnetΔ 23.7
    SWE-bench Verified: Claude 3.5 Sonnet scored 49%; Claude 4 Sonnet scored 72.7%. Claude 4 Sonnet wins this benchmark.

Operational comparison

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

MetricClaude 3.5 SonnetClaude 4 SonnetComparison
Input / output priceUSD per 1M tokensClaude 3.5 Sonnet$3 input / $15 outputClaude 4 Sonnet$3 input / $15 outputListed prices are equal.
Generation speedtokens per secondClaude 3.5 SonnetNot availableClaude 4 Sonnet40 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude 3.5 SonnetNot availableClaude 4 Sonnet1.33 sA complete latency comparison is not available.
Context windowmaximum listed tokensClaude 3.5 Sonnet200KClaude 4 Sonnet200KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkClaude 3.5 SonnetClaude 4 SonnetResult
τ²-bench resultsSource 52.3%Not comparable
Gert LabsSource 39.66%Not comparable
JobBenchSource 18.4%Not comparable
CodingClaude 4 Sonnet wins
BenchmarkClaude 3.5 SonnetClaude 4 SonnetResult
SWE-bench VerifiedSource 49%72.7%Claude 4 Sonnet leads
AA-SciCodeSource 37.3%Not comparable
Reasoning
BenchmarkClaude 3.5 SonnetClaude 4 SonnetResult
AA-LCRSource 44.3%Not comparable
CritPtSource 1.1%Not comparable
Knowledge
BenchmarkClaude 3.5 SonnetClaude 4 SonnetResult
GPQASource 59.4%Not comparable
Artificial Analysis Intelligence IndexSource 25.5%Not comparable
AA-GPQA DiamondSource 68.3%Not comparable
AA-HLESource 4.0%Not comparable
AA-Omniscience IndexSource -9.2%Not comparable
AA-Omniscience AccuracySource 22.4%Not comparable
AA-Omniscience Hallucination RateSource 40.8%Not comparable
Math
BenchmarkClaude 3.5 SonnetClaude 4 SonnetResult
FrontierMath v2 (Tiers 1-3)Source 2.069%Not comparable
FrontierMath v2 (Tier 4)Source 0.000%Not comparable
Multimodal
BenchmarkClaude 3.5 SonnetClaude 4 SonnetResult
AA-MMMU-ProSource 62.4%Not comparable
Design Arena WebsiteSource 1175Not comparable
Inst. Following
BenchmarkClaude 3.5 SonnetClaude 4 SonnetResult
AA-IFBenchSource 45.4%Not comparable
Frequently Asked Questions (2)

Which is better, Claude 3.5 Sonnet or Claude 4 Sonnet?

Claude 3.5 Sonnet is ahead on BenchLM's BenchAlign leaderboard, 47.74 to 42.79. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 49% and 72.7%.

Which is better for coding, Claude 3.5 Sonnet or Claude 4 Sonnet?

Claude 4 Sonnet has the edge for coding in this comparison, averaging 72.7 versus 49. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Related Comparisons

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.