Skip to main content
BenchLM
Advertise

Model comparison

Claude Sonnet 5 vs GPT-5.3 Codex

Data verified

Head-to-head evidence from 15 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

65.32/100
Margin
1.4pts
winning →
66.69/100
2 category wins0 category wins

Public leaderboard positions: Claude Sonnet 5 #29 (Estimated); GPT-5.3 Codex #26 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Sonnet 5 and GPT-5.3 Codex share 15 comparable benchmark results. 2 of 8 categories are comparable. 21 results are unique to Claude Sonnet 5; 6 to GPT-5.3 Codex.

Updated July 23, 2026
Shared results
15
Claude Sonnet 5 only
21
GPT-5.3 Codex only
6
Comparable categories
2 / 8

Pick GPT-5.3 Codex if you want the stronger benchmark profile. Claude Sonnet 5 only becomes the better choice if agentic is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 15 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

GPT-5.3 Codex has the cleaner BenchAlign overall profile here, landing at 66.69 versus 65.32. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

GPT-5.3 Codex is also the more expensive model on tokens at $1.75 input / $14.00 output per 1M tokens, versus $2.00 input / $10.00 output per 1M tokens for Claude Sonnet 5. Claude Sonnet 5 gives you the larger context window at 1M, compared with 400K for GPT-5.3 Codex.

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 GPT-5.3 Codex
CategoryClaude Sonnet 5ΔGPT-5.3 Codex
AgenticClaude Sonnet 581.9Margin← 10.5GPT-5.3 Codex71.4
CodingClaude Sonnet 576.7Margin← 9.5GPT-5.3 Codex67.2
KnowledgeClaude Sonnet 557.4MarginNo overlapGPT-5.3 CodexNot measured
MultimodalClaude Sonnet 588.3MarginNo overlapGPT-5.3 CodexNot measured

Decisive benchmark drivers

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

More
A · Claude Sonnet 5B · GPT-5.3 Codex

  1. OSWorld-Verified

    Agentic
    Source ↗
    A 81.2%B 64.7%
    Winner: Claude Sonnet 5Δ 16.5
    OSWorld-Verified: Claude Sonnet 5 scored 81.2%; GPT-5.3 Codex scored 64.7%. Claude Sonnet 5 wins this benchmark.

  2. SWE-bench Pro

    Coding
    Source ↗
    A 63.2%B 56.8%
    Winner: Claude Sonnet 5Δ 6.4
    SWE-bench Pro: Claude Sonnet 5 scored 63.2%; GPT-5.3 Codex scored 56.8%. Claude Sonnet 5 wins this benchmark.

  3. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 80.4%B 77.3%
    Winner: Claude Sonnet 5Δ 3.1
    Terminal-Bench 2.0: Claude Sonnet 5 scored 80.4%; GPT-5.3 Codex scored 77.3%. Claude Sonnet 5 wins this benchmark.

  4. SWE-bench Verified

    Coding
    Source ↗
    A 85.2%B 85%
    Winner: Claude Sonnet 5Δ 0.2
    SWE-bench Verified: Claude Sonnet 5 scored 85.2%; GPT-5.3 Codex scored 85%. 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 5GPT-5.3 CodexComparison
Input / output priceUSD per 1M tokensClaude Sonnet 5$2 input / $10 outputGPT-5.3 Codex$1.75 input / $14 outputClaude Sonnet 5 has the lower combined listed price.
Generation speedtokens per secondClaude Sonnet 5Not availableGPT-5.3 Codex79 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Sonnet 5Not availableGPT-5.3 Codex88.26 sA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Sonnet 51MGPT-5.3 Codex400KClaude Sonnet 5 lists the larger context window.

Benchmark Deep Dive

AgenticClaude Sonnet 5 wins
BenchmarkClaude Sonnet 5GPT-5.3 CodexResult
Terminal-Bench 2.0Source 80.4%77.3%Claude Sonnet 5 leads
BrowseCompSource 84.7%—Not comparable
HLE w/ toolsSource 57.4%—Not comparable
OSWorld-VerifiedSource 81.2%64.7%Claude Sonnet 5 leads
GDPval-AASource 1607—Not comparable
AA Agentic IndexSource 46.7%—Not comparable
GDPval-AASource 55.4%—Not comparable
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
τ²-bench resultsSource —86%Not comparable
Gert LabsSource —57.47%Not comparable
JobBenchSource —33.7%Not comparable
CodingClaude Sonnet 5 wins
BenchmarkClaude Sonnet 5GPT-5.3 CodexResult
SWE-bench VerifiedSource 85.2%85%Claude Sonnet 5 leads
SWE-bench ProSource 63.2%56.8%Claude Sonnet 5 leads
SWE MultilingualSource 78.3%—Not comparable
SWE MultimodalSource 28.1%—Not comparable
Terminal-Bench 2.0Source 80.4%—Not comparable
FrontierCode 1.1 MainSource 42.7%—Not comparable
cursorBench32Source 61.5%—Not comparable
AA Coding IndexSource 71.5%—Not comparable
AA-SciCodeSource 53.6%53.2%Claude Sonnet 5 leads
SWE-RebenchSource —58.2%Not comparable
Vibe Code BenchSource —61.77%Not comparable
Reasoning
BenchmarkClaude Sonnet 5GPT-5.3 CodexResult
AA-LCRSource 70.7%74.0%GPT-5.3 Codex leads
CritPtSource 16.9%16.9%Tie
Knowledge
BenchmarkClaude Sonnet 5GPT-5.3 CodexResult
HLESource 57.4%—Not comparable
HLE w/o toolsSource 43.2%—Not comparable
Artificial Analysis Intelligence IndexSource 53.4%44.3%Claude Sonnet 5 leads
AA-GPQA DiamondSource 91.1%91.5%GPT-5.3 Codex leads
AA-HLESource 39.6%39.9%GPT-5.3 Codex leads
AA-Omniscience IndexSource 15.3%9.9%Claude Sonnet 5 leads
AA-Omniscience AccuracySource 38.3%51.8%GPT-5.3 Codex leads
AA-Omniscience Hallucination RateSource 37.3%86.9%Claude Sonnet 5 leads
Multimodal
BenchmarkClaude Sonnet 5GPT-5.3 CodexResult
CharXivSource 88.3%—Not comparable
CharXiv w/o toolsSource 77%—Not comparable
AA-MMMU-ProSource 77.3%78.5%GPT-5.3 Codex leads
Design Arena WebsiteSource 13141193Claude Sonnet 5 leads
Inst. Following
BenchmarkClaude Sonnet 5GPT-5.3 CodexResult
AA-IFBenchSource —75.4%Not comparable
Frequently Asked Questions (3)

Which is better, Claude Sonnet 5 or GPT-5.3 Codex?

GPT-5.3 Codex is ahead on BenchLM's BenchAlign leaderboard, 66.69 to 65.32. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 81.2% and 64.7%.

Which is better for coding, Claude Sonnet 5 or GPT-5.3 Codex?

Claude Sonnet 5 has the edge for coding in this comparison, averaging 76.7 versus 67.2. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Sonnet 5 or GPT-5.3 Codex?

Claude Sonnet 5 has the edge for agentic tasks in this comparison, averaging 81.9 versus 71.4. Inside this category, OSWorld-Verified 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.