BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases9

GPT-5.3-Codex vs o3

Full profiles: GPT-5.3-Codex (OpenAI) and o3 (OpenAI): every benchmark, price and rank.

Updated · Data from 14 sources

As of 29 Oct 2026, GPT-5.3-Codex and o3 are neck and neck on quality (62.9 vs 61.0 on the BenchLeader Index, inside the ±7.6 margin), and o3 is 1.4× cheaper at $3.50 vs $4.81 per 1M tokens blended. GPT-5.3-Codex leads in every category we measure both in. o3 streams ~1.5× faster.

Key facts (as of 29 Oct 2026)

  • GPT-5.3-Codex scores 62.9 on the BenchLeader Index and o3 scores 61.0 (BenchLeader, 29 Oct 2026).
  • GPT-5.3-Codex costs $4.81 per 1M tokens blended (list price, 29 Oct 2026).
  • o3 costs $3.50 per 1M tokens blended (list price, 29 Oct 2026).
  • o3 streams ~1.5× faster than GPT-5.3-Codex (Artificial Analysis, 7-day median, 29 Oct 2026).
  • Of the 9 benchmarks both models have, GPT-5.3-Codex leads 9 (BenchLeader, 29 Oct 2026).
GPT-5.3-Codex benchmarks xhigh OpenAI o3 benchmarks OpenAIOpen in the comparison tool

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingEither61 vs 62 category scoreEither
Agents & tool useGPT-5.3-Codex80 vs 70 category score; Terminal-Bench Hard 53.0% vs 37.1%High
Long documentsGPT-5.3-Codex67 vs 62 category score; AA-LCR v1.1 83.3% vs 74.7%Medium
Images and other mediaGPT-5.3-Codex61 vs 57 category score; MMMU-Pro 78.5% vs 70.1%Medium
Following instructionsGPT-5.3-Codex74 vs 65 category score; IFBench 75.4% vs 71.4%High
Chat quality (human preference)–Only o3 has an Arena rating (61 category score)Not comparable
Lowest costo3$3.50 vs $4.81 per 1M blended; agentic coding session $0.152 vs $0.161–
Fastest first answero35.6 s (o3) vs 54.4 s (GPT-5.3-Codex (xhigh)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • GPT-5.3-Codex (xhigh) and o3 are neck and neck on quality (62.9 vs 61.0, within the ±7.6 margin).
  • GPT-5.3-Codex (xhigh) is stronger in agents & tools, instruction following, long context, multimodal.
  • o3 is stronger in coding, human preference, knowledge, maths, reasoning.
  • o3 is 1.4× cheaper ($3.50 vs $4.81 per 1M blended).
  • o3 streams 1.9× faster (151 vs 80 tokens per second).

At a glance

SpecGPT-5.3-Codexo3
DeveloperOpenAIOpenAI
Released5 Feb 202616 Apr 2025
Context window (tokens)400,000200,000
Compared atGPT-5.3-Codex (xhigh)o3
Open weightsNoNo
Price in / out / cached input per 1M$1.75 / $14.00 / $0.175$2.00 / $8.00 / $0.500

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryGPT-5.3-Codex (xhigh)o3Leader
Reasoning–60.9not comparable
Coding60.961.8level
Agents & tools80.070.3GPT-5.3-Codex
Maths–70.5not comparable
Knowledge–56.1not comparable
Instruction following73.565.1GPT-5.3-Codex
Human preference–61.1not comparable
Multimodal61.256.7GPT-5.3-Codex
Long context66.662.1GPT-5.3-Codex

Where sources disagree

Across the 9 benchmarks both have, GPT-5.3-Codex leads 9, o3 leads 0.

Overall indexGPT-5.3-Codex (xhigh)o3Leader
BenchLeader Index62.961.0neck and neck

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.

MeasureGPT-5.3-Codex (xhigh)o3
Blended price per 1M tokens$4.81$3.50
Input / output per 1M$1.75 / $14.00$2.00 / $8.00
Cached input per 1M$0.175$0.500
Price per task: chat reply$0.0049$0.0032
Price per task: summarize a 30-page report$0.029$0.029
Price per task: code edit$0.032$0.024
Price per task: agentic coding session$0.161$0.152
Price per task: structured extraction$0.0063$0.0056
Output speed80 tok/s151 tok/s
Time to first answer54.4 s5.6 s
Time to a complete answer60.6 s8.9 s

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.3-Codex (xhigh) scores 62.9 and takes 54 s to its first answer token. o3 scores 61.0 and takes 6 s to its first answer token; o3 (high) scores 53.8 in 6 s, o3 (medium) scores 53.3 in 6 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

98 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherGPT-5.3-Codex (xhigh)o3
BenchLeader IndexBenchLeader62.961.0
Agents & tools scoreBenchLeader80.070.3
Coding scoreBenchLeader60.961.8
Instruction following scoreBenchLeader73.565.1
Long context scoreBenchLeader66.662.1
Multimodal scoreBenchLeader61.256.7
Human preference scoreBenchLeader–61.1
Knowledge scoreBenchLeader–56.1
Maths scoreBenchLeader–70.5
Reasoning scoreBenchLeader–60.9
Blended price $/MBenchLeader$4.81$3.50
Output speedBenchLeader80 tok/s151 tok/s
Time to first answerBenchLeader54.4 s5.6 s
Context windowBenchLeader400,000 tokens200,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–81.8%†
Humanity's Last ExamScale AI / CAIS–20.3%†
SimpleBenchSimpleBench–53.1%†
Arena Hard PromptsArena (LMArena)–1441
GPQA Diamond (AA)Artificial Analysis91.5%82.7%
Humanity's Last Exam (AA)Artificial Analysis42.5%20.1%
GPQA Diamond (Vals)Vals AI–84.1%†
Kagi LLM BenchmarkKagi LLM Benchmark–67.6%
GPQA Diamond (HELM)HELM Capabilities–75.3%
ARC-AGI-1ARC Prize–60.8%†
ARC-AGI-2ARC Prize–6.5%†
CritPtArtificial Analysis16.9%1.1%
SciPredictScale AI SEAL–17.9%
Chess PuzzlesEpoch AI Benchmarking Hub–36.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub–29.0%†
CL-benchEpoch AI Benchmarking Hub–17.8%†
LMCAEpoch AI Benchmarking Hub–39.7%†
DTBenchEpoch AI Benchmarking Hub–84.8%†
ForecastBenchForecastBench–64.6%
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub74.8%†62.3%†
WeirdMLWeirdML77.9%52.4%†
GSO-BenchGSO-Bench–8.8%†
Arena CodingArena (LMArena)–1460
Arena WebDevArena (LMArena)1407†–
LiveCodeBenchVals AI87.3%83.9%†
Show all 98 benchmarks
MetricPublisherGPT-5.3-Codex (xhigh)o3
Coding
IOIVals AI53.8%–
SWE-bench (Vals)Vals AI78.0%–
Aider PolyglotAider polyglot leaderboard–81.3%
SWE-bench Verified (bash only)SWE-bench–58.4%
SWE-bench Verified (any scaffold)SWE-bench–58.4%
Vibe Code Bench v1.1Vals AI61.8%–
CadEvalEpoch AI Benchmarking Hub–74.0%†
ALE-BenchEpoch AI Benchmarking Hub1655.2933.5†
LiveCodeBench (AA)Artificial Analysis–80.8%
Agents & tools
Terminal-BenchTerminal-Bench78.4%†–
GDPvalOpenAI–30.8%†
Terminal-Bench HardArtificial Analysis53.0%37.1%
τ²-Bench Telecom (AA)Artificial Analysis86.0%80.7%
HiL-BenchScale AI SEAL4.3%†–
BFCL OverallBerkeley Function Calling Leaderboard–63.0%
Terminal-Bench 2.0 (Vals)Vals AI64.0%†–
DeepResearch BenchDeepResearch Bench–45.2%†
METR Time HorizonsMETR74.5%†63.6%
Vending-Bench 2Andon Labs5940.1†–
AA-Briefcase v1.1Artificial Analysis868–
BrowseComp-PlusBrowseComp-Plus–50.5%
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–33.3%†
OTIS Mock AIMEEpoch AI Benchmarking Hub–83.9%†
MATH Level 5Epoch AI Benchmarking Hub–97.8%†
AIME (Vals)Vals AI–85.3%†
MGSMVals AI–91.8%†
IMO 2025MathArena–16.7%†
Omni-MATH (HELM)HELM Capabilities–71.4%
MATH 500Vals AI–94.6%†
Arena MathsArena (LMArena)–1448
AIME 2025 (AA)Artificial Analysis–88.3%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–49.4%†
MMLU-ProVals AI–85.6%†
LegalBenchVals AI–83.8%†
CorpFinVals AI–59.7%†
TaxEvalVals AI–74.6%†
MedQAVals AI–96.1%†
PRBench FinanceScale AI SEAL–47.7%
PRBench LegalScale AI SEAL–48.6%
MultiNRCScale AI SEAL–45.5%†
MMLU-Pro (HELM)HELM Capabilities–85.9%
MedCodeVals AI–47.3%†
MedScribeVals AI–76.7%†
Instruction following
IFBenchArtificial Analysis75.4%71.4%
MultiChallengeScale AI SEAL–56.6%†
TutorBenchScale AI SEAL–52.1%†
IFEval (HELM)HELM Capabilities–86.9%
WildBench (HELM)HELM Capabilities–86.1%
Arena Instruction FollowingArena (LMArena)–1403
Human preference
Arena TextArena (LMArena)–1432
Arena Creative WritingArena (LMArena)–1383
Arena Multi-turnArena (LMArena)–1420
Arena Longer QueriesArena (LMArena)–1411
Lech Mazur Creative WritingLech Mazur–83.9%†
Multimodal
Arena VisionArena (LMArena)–1214
MMMU-ProArtificial Analysis78.5%70.1%
VISTAScale AI SEAL–50.1%†
MMMU (validation)MMMU–82.9%
MMMU-Pro (official)MMMU–76.4%
MMMU-Pro (Vals)Vals AI–80.4%†
MortgageTaxVals AI–65.7%†
VTBScale AI SEAL–13.7%
GeoBenchGeoBench–60.0%†
VPCTEpoch AI Benchmarking Hub–52.0%†
Long context
Fiction.LiveBench 120kFiction.live–100.0%†
AA-LCR v1.1Artificial Analysis83.3%74.7%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub157.1†146.8
AA Intelligence Index v4.3.2Artificial Analysis32.520.2
AA Progress Index v1Artificial Analysis301.3258.3
HELM Capabilities meanHELM Capabilities–81.1%
Safety & honesty
FORTRESSScale AI SEAL–16.0%
MASKScale AI SEAL–84.5%†
PropensityBenchScale AI SEAL–10.5%

Data as of 2026-10-29. Best configuration of each model; every score links to its source on the model pages.

What changed

  • GPT-5.3-Codex (xhigh): 1 new result (AA-Briefcase v1.1).
  • GPT-5.3-Codex (xhigh): 1 new result (AA Progress Index v1).
  • o3: 1 new result (AA Progress Index v1).
  • o3: 1 score revision.
  • o3: 1 new result (PRBench Legal).
  • o3: 1 new result (VTB).
  • o3: 1 new result (PRBench Legal).
  • o3: 1 new result (PRBench Finance).
  • o3: 1 new result (SciPredict).
  • o3: 1 new result (PRBench Finance).

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

GPT-5.3-Codex vs o3: questions

Is GPT-5.3-Codex better than o3?
GPT-5.3-Codex (xhigh) and o3 are neck and neck on quality (62.9 vs 61.0, within the ±7.6 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 29 Oct 2026, so check the category scores for your use.
GPT-5.3-Codex vs o3: which is cheaper, and will that change?
o3 is cheaper today: $3.50 against $4.81 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-5.3-Codex or o3 better for coding?
They are level in coding (61 vs 62 on the category index).
Which is faster, GPT-5.3-Codex or o3?
o3 streams ~1.5× faster (151 vs 80 output tokens per second, Artificial Analysis 7-day median).
Is GPT-5.3-Codex or o3 better for agents and tool use?
GPT-5.3-Codex scores higher in agentic tasks (80 vs 70 on the category index, where 50 is average). On Terminal-Bench Hard, the top shared agents & tools benchmark, it is 53.0% for GPT-5.3-Codex against 37.1% for o3.
More questions (4)
Which is better for long documents?
GPT-5.3-Codex scores higher on long-context benchmarks (67 vs 62). GPT-5.3-Codex accepts more context: 400,000 against 200,000 tokens for o3.
Which has lower latency?
o3 answers first: 5.6 s against 54.4 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on GPT-5.3-Codex vs o3?
Across the 9 benchmarks both have, GPT-5.3-Codex leads 9, o3 leads 0.
When was GPT-5.3-Codex released?
GPT-5.3-Codex was released on 5 Feb 2026.