Data as of October 17, 2026 · How the score is built
GPT-5.3 Codex
Decision readingGPT-5.3 Codex scores 60.5 out of 100 and ranks #54 of 224. This profile shows 11 source-displayable benchmark rows; its strongest eligible category is Coding at #35. API pricing is $1.75 input and $14 output per million tokens.
Released Feb 5, 2026 — see all recent releases
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
60.5/100
field median 49.6#54 of 224 ranked models
Public
#54of 224
Verified #36 of 88
Price
$1.75input / $14 output
input median $0.75blended $7.88
Speed
101tok/s
field median 92 tok/sFirst token 61 s
Context
400Ktokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Coding ranks #35. Particularly well-suited for software development and code generation tasks.
Validate before choosing
11 published rows leave some tracked benchmark slots empty. Agentic is its lowest eligible category at #41.
Source-linked · 11 displayable benchmark rows
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #41 of 128Percentile 69thWeight 22%4 benchmarksVerified | 55.5 | 4 benchmarks | Verified | |||
| CodingRank #35 of 150Percentile 77thWeight 20%7 benchmarksVerified | 53.5 | 7 benchmarks | Verified | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
11 of 681 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic4/4 verified
- Coding7/7 verified
- ReasoningNot measured
- MultimodalNot measured
- KnowledgeNot measured
- MultilingualNot measured
- Inst. FollowingNot measured
- MathNot measured
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
GPT-5.3 Codex category percentile values
- Agentic69th percentile
- Coding77th percentile
- ReasoningNot eligible
- MultimodalNot eligible
- KnowledgeNot eligible
- MultilingualNot eligible
- Instruction followingNot eligible
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#41/128
- Coding#35/150
- ReasoningNot ranked
- MultimodalNot ranked
- KnowledgeNot ranked
- MultilingualNot ranked
- Inst. FollowingNot ranked
- MathNot ranked
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding7 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE-bench Pro | Score56.8% | Versus best verified row Best verified: Claude Opus 5.5 · 89.9% | Gap33.1 behind | Weight26% ref. weight | Provider exact |
| LiveCodeBench (Vals)LiveCodeBench, Vals AI run | Score87.3% | Versus best verified row Best verified: Claude Fable 5.1 · 90.5% | Gap3.2 behind | Weight8% ref. weight | |
| SWE-Rebench | Score58.2% | Versus best verified row Best verified: Claude Opus 4.6 · 65.3% | Gap7.1 behind | Weight5% ref. weight | Benchmark exact |
| Terminal-Bench 2.0 | Score77.3% | Versus best verified row Best verified: GPT-5.5 · 82.0% | Gap4.7 behind | WeightScored in Agentic | Provider exact |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score85% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap11 behind | WeightDisplay only | Provider exact |
| Vibe Code BenchVibe Code Bench v1.1 | Score61.77% | Versus best verified row Best verified: Gemini 4 Argon · 91.90% | Gap30.1 behind | WeightDisplay only | Benchmark exact |
| SWE-bench (Vals)SWE-bench, Vals AI run | Score78.0% | Versus best verified row Best verified: Claude Opus 5 · 97.0% | Gap19 behind | WeightDisplay only | Verified |
Agentic4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | Score77.3% | Versus best verified row Best verified: GPT-5.5 · 82% | Gap4.7 behind | Weight7% ref. weight | Provider exact |
| OSWorld-Verified | Score64.7% | Versus best verified row Best verified: Qwen3.8 Max · 86.1% | Gap21.4 behind | Weight7% ref. weight | Provider exact |
| JobBench | Score33.7% | Versus best verified row Best verified: Muse Wonder Full · 75.3% | Gap41.6 behind | Weight6% ref. weight | Benchmark exact |
| Gert LabsGert Labs Composite Game Benchmark | Score57.47% | Versus best verified row Best verified: Claude Opus 4.8 · 72.97% | Gap15.5 behind | WeightDisplay only | Benchmark exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 11 rowsWhat it costs to get this score
Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.
GPT-5.3 Codex · 60.5 score · $7.88 blended per million tokens
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Horizontal: blended price per million tokens, log scale · Vertical: public score
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
GPT-5.3-Codex-SparkSpec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- gpt-5.3-codexOpenAI GPT-5.3 Codex model documentation
- Context window
- 400KOpenAI GPT-5.3 Codex model documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, imageOpenAI model catalog
- Output modalities
- textOpenAI model catalog
- Parameters
- Not disclosed by the provider
- Availability
- OpenAI Responses APIOpenAI model catalog
- Cloud regions
- Not tracked yet
- Lifecycle
- activeOpenAI GPT-5.3 Codex model documentation
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
GPT-5.3 Codex ranks #54 of 224 on the public leaderboard with a score of 60.48/100. Its source-verified position is #36 of 88.
GPT-5.3 Codex is a proprietary model with a 400K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
GPT-5.3 Codex sits in the GPT-5.3 Codex family with GPT-5.3-Codex-Spark. 11 of 681 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Coding at #35, while its lowest eligible position is Agentic at #41. particularly well-suited for software development and code generation tasks.
Last updated October 17, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does GPT-5.3 Codex perform overall in AI benchmarks?
GPT-5.3 Codex ranks #54 out of 224 models on the public BenchAlign leaderboard, with a score of 60.48/100. Its evidence status is Supported, and this profile shows 11 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is GPT-5.3 Codex good for coding and programming?
GPT-5.3 Codex ranks #35 out of 150 eligible models for coding and programming, with a public category score of 53.5/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is GPT-5.3 Codex good for agentic tool use and computer tasks?
GPT-5.3 Codex ranks #41 out of 128 eligible models for agentic tool use and computer tasks, with a public category score of 55.5/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Which sibling models are related to GPT-5.3 Codex?
GPT-5.3 Codex belongs to the GPT-5.3 Codex family. Related tracked variants include GPT-5.3-Codex-Spark. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does GPT-5.3 Codex have full benchmark coverage on BenchLM?
No. GPT-5.3 Codex currently has 23 source-displayable rows across 681 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of GPT-5.3 Codex?
GPT-5.3 Codex has a documented context window of 400K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.