Skip to main content
BenchLM
Advertise

Model comparison

Claude Sonnet 5 vs Step 3.7 Flash

Data verified

Head-to-head evidence from 20 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

65.32/100
Margin
14.4pts
← winning
50.87/100
2 category wins0 category wins

Public leaderboard positions: Claude Sonnet 5 #29 (Estimated); Step 3.7 Flash #110 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Sonnet 5 and Step 3.7 Flash share 20 comparable benchmark results. 2 of 8 categories are comparable. 16 results are unique to Claude Sonnet 5; 9 to Step 3.7 Flash.

Updated July 23, 2026
Shared results
20
Claude Sonnet 5 only
16
Step 3.7 Flash only
9
Comparable categories
2 / 8

Pick Claude Sonnet 5 if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 20 shared benchmark results across 5 evidence categories; 2 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 is clearly ahead on the BenchAlign aggregate, 65.32 to 50.87. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Claude Sonnet 5's sharpest advantage is in coding, where it averages 76.7 against 56.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 80.4% to 59.5%.

Claude Sonnet 5 is also the more expensive model on tokens at $2.00 input / $10.00 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. That is roughly 8.7x on output cost alone. Claude Sonnet 5 gives you the larger context window at 1M, compared with 256K for Step 3.7 Flash.

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 5 and Step 3.7 Flash
CategoryClaude Sonnet 5ΔStep 3.7 Flash
CodingClaude Sonnet 576.7Margin← 20.4Step 3.7 Flash56.3
AgenticClaude Sonnet 581.9Margin← 15.5Step 3.7 Flash66.4
KnowledgeClaude Sonnet 557.4MarginNo overlapStep 3.7 FlashNot measured
MultimodalClaude Sonnet 588.3MarginNo overlapStep 3.7 FlashNot measured

Decisive benchmark drivers

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

More
A · Claude Sonnet 5B · Step 3.7 Flash

  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 80.4%B 59.5%
    Winner: Claude Sonnet 5Δ 20.9
    Terminal-Bench 2.0: Claude Sonnet 5 scored 80.4%; Step 3.7 Flash scored 59.5%. Claude Sonnet 5 wins this benchmark.

  2. BrowseComp

    Agentic
    Source ↗
    A 84.7%B 75.8%
    Winner: Claude Sonnet 5Δ 8.9
    BrowseComp: Claude Sonnet 5 scored 84.7%; Step 3.7 Flash scored 75.8%. Claude Sonnet 5 wins this benchmark.

  3. SWE-bench Pro

    Coding
    Source ↗
    A 63.2%B 56.3%
    Winner: Claude Sonnet 5Δ 6.9
    SWE-bench Pro: Claude Sonnet 5 scored 63.2%; Step 3.7 Flash scored 56.3%. 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 5Step 3.7 FlashComparison
Input / output priceUSD per 1M tokensClaude Sonnet 5$2 input / $10 outputStep 3.7 Flash$0.2 input / $1.15 outputStep 3.7 Flash has the lower combined listed price.
Generation speedtokens per secondClaude Sonnet 5Not availableStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Sonnet 5Not availableStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Sonnet 51MStep 3.7 Flash256KClaude Sonnet 5 lists the larger context window.

Benchmark Deep Dive

AgenticClaude Sonnet 5 wins
BenchmarkClaude Sonnet 5Step 3.7 FlashResult
Terminal-Bench 2.0Source 80.4%59.5%Claude Sonnet 5 leads
BrowseCompSource 84.7%75.8%Claude Sonnet 5 leads
HLE w/ toolsSource 57.4%47.2%Claude Sonnet 5 leads
OSWorld-VerifiedSource 81.2%—Not comparable
GDPval-AASource 16071017Claude Sonnet 5 leads
AA Agentic IndexSource 46.7%21.5%Claude Sonnet 5 leads
GDPval-AASource 55.4%25.9%Claude Sonnet 5 leads
AA BriefcaseSource 1388—Not 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
DeepSearchQASource —92.8%Not comparable
ToolathlonSource —49.5%Not comparable
Claw-EvalSource —67.1%Not comparable
Gert LabsSource —51.57%Not comparable
τ²-bench resultsSource —98.5%Not comparable
APEX-Agents-AASource —14.8%Not comparable
CodingClaude Sonnet 5 wins
BenchmarkClaude Sonnet 5Step 3.7 FlashResult
SWE-bench VerifiedSource 85.2%—Not comparable
SWE-bench ProSource 63.2%56.3%Claude Sonnet 5 leads
SWE MultilingualSource 78.3%—Not comparable
SWE MultimodalSource 28.1%—Not comparable
Terminal-Bench 2.0Source 80.4%59.5%Claude Sonnet 5 leads
FrontierCode 1.1 MainSource 42.7%—Not comparable
cursorBench32Source 61.5%—Not comparable
AA Coding IndexSource 71.5%39.6%Claude Sonnet 5 leads
AA-SciCodeSource 53.6%40.0%Claude Sonnet 5 leads
Reasoning
BenchmarkClaude Sonnet 5Step 3.7 FlashResult
AA-LCRSource 70.7%63.7%Claude Sonnet 5 leads
CritPtSource 16.9%2.3%Claude Sonnet 5 leads
Knowledge
BenchmarkClaude Sonnet 5Step 3.7 FlashResult
HLESource 57.4%—Not comparable
HLE w/o toolsSource 43.2%—Not comparable
Artificial Analysis Intelligence IndexSource 53.4%30.3%Claude Sonnet 5 leads
AA-GPQA DiamondSource 91.1%80.9%Claude Sonnet 5 leads
AA-HLESource 39.6%19.9%Claude Sonnet 5 leads
AA-Omniscience IndexSource 15.3%-37.5%Claude Sonnet 5 leads
AA-Omniscience AccuracySource 38.3%25.4%Claude Sonnet 5 leads
AA-Omniscience Hallucination RateSource 37.3%84.4%Claude Sonnet 5 leads
Multimodal
BenchmarkClaude Sonnet 5Step 3.7 FlashResult
CharXivSource 88.3%—Not comparable
CharXiv w/o toolsSource 77%—Not comparable
AA-MMMU-ProSource 77.3%75.3%Claude Sonnet 5 leads
Design Arena WebsiteSource 13141211Claude Sonnet 5 leads
SimpleVQASource —79.2%Not comparable
V*Source —95.3%Not comparable
Inst. Following
BenchmarkClaude Sonnet 5Step 3.7 FlashResult
AA-IFBenchSource —67.3%Not comparable
Frequently Asked Questions (3)

Which is better, Claude Sonnet 5 or Step 3.7 Flash?

Claude Sonnet 5 is ahead on BenchLM's BenchAlign leaderboard, 65.32 to 50.87. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 80.4% and 59.5%.

Which is better for coding, Claude Sonnet 5 or Step 3.7 Flash?

Claude Sonnet 5 has the edge for coding in this comparison, averaging 76.7 versus 56.3. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Sonnet 5 or Step 3.7 Flash?

Claude Sonnet 5 has the edge for agentic tasks in this comparison, averaging 81.9 versus 66.4. Inside this category, GDPval-AA 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.