Skip to main content
BenchLM
Advertise

Model comparison

GPT-5.3 Codex vs GPT-5.5

Data verified

Head-to-head evidence from 19 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

66.69/100
Margin
6.8pts
winning →
GPT-5.5
OpenAI
73.51/100
1 category wins1 category wins

Public leaderboard positions: GPT-5.3 Codex #26 (Supported); GPT-5.5 #9 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GPT-5.3 Codex and GPT-5.5 share 19 comparable benchmark results. 2 of 8 categories are comparable. 2 results are unique to GPT-5.3 Codex; 38 to GPT-5.5.

Updated July 22, 2026
Shared results
19
GPT-5.3 Codex only
2
GPT-5.5 only
38
Comparable categories
2 / 8

Pick GPT-5.5 if you want the stronger benchmark profile. GPT-5.3 Codex only becomes the better choice if coding is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 19 shared benchmark results across 6 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-5.5 is clearly ahead on the BenchAlign aggregate, 73.51 to 66.69. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.5's sharpest advantage is in agentic, where it averages 81.6 against 71.4. The single biggest benchmark swing on the page is OSWorld-Verified, 64.7% to 78.7%. GPT-5.3 Codex does hit back in coding, so the answer changes if that is the part of the workload you care about most.

GPT-5.5 is also the more expensive model on tokens at $5.00 input / $30.00 output per 1M tokens, versus $1.75 input / $14.00 output per 1M tokens for GPT-5.3 Codex. That is roughly 2.1x on output cost alone. GPT-5.5 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 GPT-5.3 Codex and GPT-5.5
CategoryGPT-5.3 CodexΔGPT-5.5
AgenticGPT-5.3 Codex71.4Margin→ 10.2GPT-5.581.6
CodingGPT-5.3 Codex67.2Margin← 8.6GPT-5.558.6
ReasoningGPT-5.3 CodexNot measuredMarginNo overlapGPT-5.585.0
KnowledgeGPT-5.3 CodexNot measuredMarginNo overlapGPT-5.557.8
MathGPT-5.3 CodexNot measuredMarginNo overlapGPT-5.547.6
MultimodalGPT-5.3 CodexNot measuredMarginNo overlapGPT-5.570.4

Decisive benchmark drivers

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

More
A · GPT-5.3 CodexB · GPT-5.5

  1. OSWorld-Verified

    Agentic
    Source ↗
    A 64.7%B 78.7%
    Winner: GPT-5.5Δ 14
    OSWorld-Verified: GPT-5.3 Codex scored 64.7%; GPT-5.5 scored 78.7%. GPT-5.5 wins this benchmark.

  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 77.3%B 82%
    Winner: GPT-5.5Δ 4.7
    Terminal-Bench 2.0: GPT-5.3 Codex scored 77.3%; GPT-5.5 scored 82%. GPT-5.5 wins this benchmark.

  3. SWE-bench Pro

    Coding
    Source ↗
    A 56.8%B 58.6%
    Winner: GPT-5.5Δ 1.8
    SWE-bench Pro: GPT-5.3 Codex scored 56.8%; GPT-5.5 scored 58.6%. GPT-5.5 wins this benchmark.

Operational comparison

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

MetricGPT-5.3 CodexGPT-5.5Comparison
Input / output priceUSD per 1M tokensGPT-5.3 Codex$1.75 input / $14 outputGPT-5.5$5 input / $30 outputGPT-5.3 Codex has the lower combined listed price.
Generation speedtokens per secondGPT-5.3 Codex79 tok/sGPT-5.5Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGPT-5.3 Codex88.26 sGPT-5.5Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensGPT-5.3 Codex400KGPT-5.51MGPT-5.5 lists the larger context window.

Benchmark Deep Dive

AgenticGPT-5.5 wins
BenchmarkGPT-5.3 CodexGPT-5.5Result
Terminal-Bench 2.0Source 77.3%82%GPT-5.5 leads
OSWorld-VerifiedSource 64.7%78.7%GPT-5.5 leads
τ²-bench resultsSource 86%93.9%GPT-5.5 leads
Gert LabsSource 57.47%72.93%GPT-5.5 leads
JobBenchSource 33.7%42.7%GPT-5.5 leads
CyberGymSource —81.8%Not comparable
BrowseCompSource —84.4%Not comparable
MCP AtlasSource —75.3%Not comparable
ToolathlonSource —55.6%Not comparable
AA Agentic IndexSource —44.9%Not comparable
APEX-Agents-AASource —37.7%Not comparable
GDPval-AASource —49.5%Not comparable
GDPval-AASource —1490Not comparable
ResearchClawBenchSource —17.0%Not comparable
OSWorld 2.0Source —13.0%Not comparable
ExploitGymSource —13.4%Not comparable
AA BriefcaseSource —1154Not comparable
AA AutomationBenchSource —42.1%Not comparable
AA EnterpriseOps-GymSource —46.6%Not comparable
AA Harvey LABSource —86.3%Not comparable
AA ITBenchSource —45.8%Not comparable
AA Tau3 BankingSource —31.3%Not comparable
terminalBenchHardSource —60.6%Not comparable
aaTerminalBench21Source —84.3%Not comparable
CodingGPT-5.3 Codex wins
BenchmarkGPT-5.3 CodexGPT-5.5Result
SWE-bench VerifiedSource 85%—Not comparable
SWE-bench ProSource 56.8%58.6%GPT-5.5 leads
SWE-RebenchSource 58.2%—Not comparable
Vibe Code BenchSource 61.77%69.85%GPT-5.5 leads
AA-SciCodeSource 53.2%56.1%GPT-5.5 leads
Terminal-Bench 2.0Source —82.0%Not comparable
React Native EvalsSource —84.7%Not comparable
cursorBench31Source —59.2%Not comparable
cursorBench32Source —58.4%Not comparable
AA Coding IndexSource —74.9%Not comparable
FrontierCode 1.1 MainSource —43.0%Not comparable
Reasoning
BenchmarkGPT-5.3 CodexGPT-5.5Result
AA-LCRSource 74.0%74.3%GPT-5.5 leads
CritPtSource 16.9%27.1%GPT-5.5 leads
MRCR v2 64K-128KSource —83.1%Not comparable
MRCR v2 128K-256KSource —87.5%Not comparable
ARC-AGI-2Source —85%Not comparable
Knowledge
BenchmarkGPT-5.3 CodexGPT-5.5Result
Artificial Analysis Intelligence IndexSource 44.3%54.8%GPT-5.5 leads
AA-GPQA DiamondSource 91.5%93.5%GPT-5.5 leads
AA-HLESource 39.9%44.3%GPT-5.5 leads
AA-Omniscience IndexSource 9.9%20.1%GPT-5.5 leads
AA-Omniscience AccuracySource 51.8%56.9%GPT-5.5 leads
AA-Omniscience Hallucination RateSource 86.9%85.5%GPT-5.5 leads
GPQASource —93.6%Not comparable
GPQA-DSource —93.6%Not comparable
HLESource —52.2%Not comparable
HLE w/o toolsSource —41.4%Not comparable
Math
BenchmarkGPT-5.3 CodexGPT-5.5Result
FrontierMath (legacy)Source —51.7%Not comparable
FrontierMath v2 (Tiers 1-3)Source —51.700%Not comparable
FrontierMath v2 (Tier 4)Source —35.400%Not comparable
Multimodal
BenchmarkGPT-5.3 CodexGPT-5.5Result
AA-MMMU-ProSource 78.5%79.9%GPT-5.5 leads
Design Arena WebsiteSource 11931282GPT-5.5 leads
MMMU-ProSource —81.2%Not comparable
MMMU-Pro w/ PythonSource —83.2%Not comparable
OfficeQA ProSource —54.1%Not comparable
Inst. Following
BenchmarkGPT-5.3 CodexGPT-5.5Result
AA-IFBenchSource 75.4%75.9%GPT-5.5 leads
Frequently Asked Questions (3)

Which is better, GPT-5.3 Codex or GPT-5.5?

GPT-5.5 is ahead on BenchLM's BenchAlign leaderboard, 73.51 to 66.69. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 64.7% and 78.7%.

Which is better for coding, GPT-5.3 Codex or GPT-5.5?

GPT-5.3 Codex has the edge for coding in this comparison, averaging 67.2 versus 58.6. Inside this category, Vibe Code Bench is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5.3 Codex or GPT-5.5?

GPT-5.5 has the edge for agentic tasks in this comparison, averaging 81.6 versus 71.4. Inside this category, Gert Labs is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

OpenAI Compare Pricing Methodology Find Your Best LLM Overall Rankings
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.