Skip to main content

Model profile

GPT-5.2-Codex

OpenAIEstablishedReleased Dec 18, 2025
Data verified
Overall Score
59.1Public #58 of 200Verified #43 of 99
Arena Elo
1331
Eligible category ranks
2of 8
Price (1M tokens)
$1.75 in / $14 out
API pricing
Speed
123tok/s
Context
400K

Evidence coverage

15 of 321 tracked benchmarks are published. 3 are verified and 12 provisional. 6 of 8 categories are measured.

Updated July 20, 2026Methodology
Published / tracked
15 / 321
Verified
3
Provisional
12
Categories with evidence
6 / 8

Evidence by category

  • Agentic3 benchmarks
    Mixed evidence
  • Coding2 benchmarks
    Mixed evidence
  • Reasoning2 benchmarks
    Reported
  • Knowledge6 benchmarks
    Reported
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal1 benchmark
    Reported
  • Inst. Following1 benchmark
    Reported
ProprietaryReasoning
Confidence:
Low
base

GPT-5.2-Codex ranks #58 out of 200 models on the public leaderboard with an overall score of 59.1/100. It also ranks #43 out of 99 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

GPT-5.2-Codex is a proprietary model with a 400K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

This profile currently has 15 of 321 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Coding (#29), while its weakest is Agentic (#30). This performance profile makes it particularly well-suited for software development and code generation tasks.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 58.8859.52

  1. MiniMax M2.5
    MiniMax
    #5559.52
    MiniMax M2.5 is #55 with a score of 59.52.
    Compare
  2. Qwen3.5 397B (Reasoning)
    Alibaba
    #5659.5
    Qwen3.5 397B (Reasoning) is #56 with a score of 59.5.
    Compare
  3. Kimi K2.5 (Reasoning)
    Moonshot AI
    #5759.35
    Kimi K2.5 (Reasoning) is #57 with a score of 59.35.
    Compare
  4. GPT-5.2-CodexCurrent model
    OpenAI
    #5859.1
    GPT-5.2-Codex is #58 with a score of 59.1.
  5. GPT-5.2 Instant
    OpenAI
    #5959.0
    GPT-5.2 Instant is #59 with a score of 59.0.
    Compare
  6. GPT-5.3 Instant
    OpenAI
    #6058.9
    GPT-5.3 Instant is #60 with a score of 58.9.
    Compare
  7. DeepSeek V4 Flash
    DeepSeek
    #6158.88
    DeepSeek V4 Flash is #61 with a score of 58.88.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Coding77%
    Eligible cohort rank #29 of 122Category score 57.9
  2. Agentic75%
    Eligible cohort rank #30 of 119Category score 53.1

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #30 of 119Percentile 75thWeight 22%3 benchmarksMixed sources53.1
CodingRank #29 of 122Percentile 77thWeight 20%2 benchmarksMixed sources57.9
ReasoningRank Not rankedWeight 17%2 benchmarksReported90.4
KnowledgeRank Not rankedWeight 12%6 benchmarksReported59.6
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank Not rankedWeight 12%1 benchmarkReported87.2
Inst. FollowingRank Not rankedWeight 5%1 benchmarkReported92.0

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1331Not availableNot available

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic3 benchmarks
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

92.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Gert LabsBenchmark exact

Gert Labs Composite Game Benchmark

51.79%Display only
Source: Gert Labs rankingsProvenance: Gert Labs reports this composite leaderboard score in the public rankings API. BenchLM scales the source gscore from 0-1 to 0-100 and stores it as a display-only agentic benchmark.
JobBenchBenchmark exact
26.0%Display only
Source: JobBench paperProvenance: JobBench reports GPT-5.2-Codex under Codex CLI on the main-set leaderboard. BenchLM stores the reported main-set score.
Coding2 benchmarks
Vibe Code BenchBenchmark exact

Vibe Code Bench v1.1

37.91%Display only
Source: Vals AI: Vibe Code Bench v1.1Provenance: Vals Vibe Code Bench v1.1 reports this exact row under openai/gpt-5.2-codex; BenchLM stores it on the local vibeCodeBench key.
AA-SciCodeReported

Artificial Analysis SciCode

54.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

75.7%Display only
Source: Artificial Analysis: artificial-analysis-long-context-reasoning leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

8.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge6 benchmarks
Artificial Analysis Intelligence IndexReported
40.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

89.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

33.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-2.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

40.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

72.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Multimodal1 benchmark
AA-MMMU-ProReported

Artificial Analysis MMMU-Pro

76.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

77.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.

Frequently Asked Questions

How does GPT-5.2-Codex perform overall in AI benchmarks?

GPT-5.2-Codex has 15 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is GPT-5.2-Codex good for knowledge and understanding?

GPT-5.2-Codex has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is GPT-5.2-Codex good for coding and programming?

GPT-5.2-Codex ranks #29 out of 122 models in coding and programming benchmarks with an average score of 57.9. There are stronger options in this category.

Is GPT-5.2-Codex good for reasoning and logic?

GPT-5.2-Codex has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is GPT-5.2-Codex good for agentic tool use and computer tasks?

GPT-5.2-Codex ranks #30 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 53.1. There are stronger options in this category.

Is GPT-5.2-Codex good for multimodal and grounded tasks?

GPT-5.2-Codex has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Is GPT-5.2-Codex good for instruction following?

GPT-5.2-Codex has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Does GPT-5.2-Codex have full benchmark coverage on BenchLM?

Not yet. GPT-5.2-Codex currently has 15 published benchmark scores out of the 321 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of GPT-5.2-Codex?

GPT-5.2-Codex has a published context window of 400K, which determines how much text it can process in a single interaction.

Last updated: July 20, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.