Skip to main content

Model comparison

Claude Sonnet 4.6 vs GPT-4.1 mini

Data verified

Head-to-head evidence from 16 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

64.4/100
Margin
21.3pts
← winning
43.1/100
3 category wins0 category wins

Public leaderboard positions: Claude Sonnet 4.6 #34 (Supported); GPT-4.1 mini #160 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Sonnet 4.6 and GPT-4.1 mini share 16 comparable benchmark results. 3 of 8 categories are comparable. 17 results are unique to Claude Sonnet 4.6; 6 to GPT-4.1 mini.

Updated July 24, 2026
Shared results
16
Claude Sonnet 4.6 only
17
GPT-4.1 mini only
6
Comparable categories
3 / 8

Pick Claude Sonnet 4.6 if you want the stronger benchmark profile. GPT-4.1 mini only becomes the better choice if you want the cheaper token bill or you need the larger 1M context window.

Confidence note. This is a partial-evidence comparison with 16 shared benchmark results across 7 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, 64.4 to 43.1. 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 coding, where it averages 69.1 against 23.6. The single biggest benchmark swing on the page is SWE-bench Verified, 79.6% to 23.6%.

Claude Sonnet 4.6 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $0.40 input / $1.60 output per 1M tokens for GPT-4.1 mini. That is roughly 9.4x on output cost alone. GPT-4.1 mini 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 GPT-4.1 mini
CategoryClaude Sonnet 4.6ΔGPT-4.1 mini
CodingClaude Sonnet 4.669.1Margin 45.5GPT-4.1 mini23.6
MathClaude Sonnet 4.626.4Margin 21.9GPT-4.1 mini4.5
KnowledgeClaude Sonnet 4.666.0Margin 1.8GPT-4.1 mini64.2
AgenticClaude Sonnet 4.665.2MarginNo overlapGPT-4.1 miniNot measured
MultimodalClaude Sonnet 4.677.4MarginNo overlapGPT-4.1 miniNot measured
Inst. FollowingClaude Sonnet 4.6Not measuredMarginNo overlapGPT-4.1 mini88.5

Decisive benchmark drivers

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

More
A · Claude Sonnet 4.6B · GPT-4.1 mini
  1. SWE-bench Verified

    Coding
    Source ↗
    A 79.6%B 23.6%
    Winner: Claude Sonnet 4.6Δ 56
    SWE-bench Verified: Claude Sonnet 4.6 scored 79.6%; GPT-4.1 mini scored 23.6%. Claude Sonnet 4.6 wins this benchmark.
  2. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 32.400%B 4.483%
    Winner: Claude Sonnet 4.6Δ 27.9
    FrontierMath v2 (Tiers 1-3): Claude Sonnet 4.6 scored 32.400%; GPT-4.1 mini scored 4.483%. Claude Sonnet 4.6 wins this benchmark.
  3. GPQA

    Knowledge
    Source ↗
    A 89.9%B 64.2%
    Winner: Claude Sonnet 4.6Δ 25.7
    GPQA: Claude Sonnet 4.6 scored 89.9%; GPT-4.1 mini scored 64.2%. 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 Sonnet 4.6GPT-4.1 miniComparison
Input / output priceUSD per 1M tokensClaude Sonnet 4.6$3 input / $15 outputGPT-4.1 mini$0.4 input / $1.6 outputGPT-4.1 mini has the lower combined listed price.
Generation speedtokens per secondClaude Sonnet 4.644 tok/sGPT-4.1 mini80 tok/sGPT-4.1 mini has the higher measured throughput.
First-answer latencyseconds to first tokenClaude Sonnet 4.61.48 sGPT-4.1 mini0.76 sGPT-4.1 mini reaches the first token sooner.
Context windowmaximum listed tokensClaude Sonnet 4.6200KGPT-4.1 mini1MGPT-4.1 mini lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkClaude Sonnet 4.6GPT-4.1 miniResult
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%52.9%Claude Sonnet 4.6 leads
Gert LabsSource 62.92%Not comparable
OSWorld 2.0Source 8.3%Not comparable
JobBenchSource 36.9%Not comparable
AA Agentic IndexSource 1.7%Not comparable
GDPval-AASource 0.4%Not comparable
GDPval-AASource 508Not comparable
CodingClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6GPT-4.1 miniResult
SWE-bench VerifiedSource 79.6%23.6%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%40.4%Claude Sonnet 4.6 leads
FrontierCode 1.1 MainSource 24.3%Not comparable
AA Coding IndexSource 20.2%Not comparable
Reasoning
BenchmarkClaude Sonnet 4.6GPT-4.1 miniResult
AA-LCRSource 57.7%42.3%Claude Sonnet 4.6 leads
CritPtSource 0.9%0.0%Claude Sonnet 4.6 leads
KnowledgeClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6GPT-4.1 miniResult
GPQASource 89.9%64.2%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%14.8%Claude Sonnet 4.6 leads
AA-GPQA DiamondSource 79.9%66.4%Claude Sonnet 4.6 leads
AA-HLESource 13.2%4.6%Claude Sonnet 4.6 leads
AA-Omniscience IndexSource -2.9%-50.1%Claude Sonnet 4.6 leads
AA-Omniscience AccuracySource 38.0%17.5%Claude Sonnet 4.6 leads
AA-Omniscience Hallucination RateSource 65.9%82.0%Claude Sonnet 4.6 leads
MMLUSource 87.5%Not comparable
MathClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6GPT-4.1 miniResult
FrontierMath v2 (Tiers 1-3)Source 32.400%4.483%Claude Sonnet 4.6 leads
FrontierMath v2 (Tier 4)Source 8.300%Not comparable
Multimodal
BenchmarkClaude Sonnet 4.6GPT-4.1 miniResult
CharXivSource 77.4%Not comparable
AA-MMMU-ProSource 70.6%58.7%Claude Sonnet 4.6 leads
Design Arena WebsiteSource 13141027Claude Sonnet 4.6 leads
Inst. Following
BenchmarkClaude Sonnet 4.6GPT-4.1 miniResult
AA-IFBenchSource 41.2%38.3%Claude Sonnet 4.6 leads
IFEvalSource 88.5%Not comparable
Frequently Asked Questions (4)

Which is better, Claude Sonnet 4.6 or GPT-4.1 mini?

Claude Sonnet 4.6 is ahead on BenchLM's BenchAlign leaderboard, 64.4 to 43.1. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 79.6% and 23.6%.

Which is better for knowledge tasks, Claude Sonnet 4.6 or GPT-4.1 mini?

Claude Sonnet 4.6 has the edge for knowledge tasks in this comparison, averaging 66 versus 64.2. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.

Which is better for coding, Claude Sonnet 4.6 or GPT-4.1 mini?

Claude Sonnet 4.6 has the edge for coding in this comparison, averaging 69.1 versus 23.6. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, Claude Sonnet 4.6 or GPT-4.1 mini?

Claude Sonnet 4.6 has the edge for math in this comparison, averaging 26.4 versus 4.5. Inside this category, FrontierMath v2 (Tiers 1-3) is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 24, 2026