Skip to main content
BenchLM
Advertise

Model profile

GPT-5.5

OpenAISupersededReleased Apr 23, 2026
Data verified
Superseded:OpenAI has released newer models in this line —GPT-5.6 Sol
Overall Score
73.51Public #9 of 200
Arena Elo
1481
Eligible category ranks
4of 8
Price (1M tokens)
$5 in / $30 out
API pricing
Speed
Not listed
Context
1M

Evidence coverage

57 of 323 tracked benchmarks are published. 32 are verified and 25 provisional. 7 of 8 categories are measured.

Updated July 22, 2026Methodology
Published / tracked
57 / 323
Verified
32
Provisional
25
Categories with evidence
7 / 8

Evidence by category

  • Agentic24 benchmarks
    Mixed evidence
  • Coding9 benchmarks
    Mixed evidence
  • Reasoning5 benchmarks
    Mixed evidence
  • Knowledge10 benchmarks
    Mixed evidence
  • Math3 benchmarks
    Verified
  • Multilingual0 benchmarks
    Not measured
  • Multimodal5 benchmarks
    Mixed evidence
  • Inst. Following1 benchmark
    Reported
ProprietaryReasoning
Confidence:
High
base

GPT-5.5 ranks #9 out of 200 models on the public leaderboard with an overall score of 73.51/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. This places it in the upper tier of AI models, with competitive scores across most benchmark categories.

GPT-5.5 is a proprietary model with a 1M 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.

GPT-5.5 sits inside the GPT-5.5 family alongside GPT-5.5 Pro. BenchLM links it directly to GPT-5.4 as the earlier related model in that lineage. This profile currently has 57 of 323 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 Agentic (#6), while its weakest is Multimodal & Grounded (#11). This performance profile makes it particularly useful for coding agents, browser research, and computer-use workflows.

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 71.04–76.72

  1. Grok 4.5
    xAI
    #776.72
    Grok 4.5 is #7 with a score of 76.72.
    Compare
  2. GPT-5.4
    OpenAI
    #874.24
    GPT-5.4 is #8 with a score of 74.24.
    Compare
  3. GPT-5.5Current model
    OpenAI
    #973.51
    GPT-5.5 is #9 with a score of 73.51.
  4. Qwen3.7 Max
    Alibaba
    #1072.84
    Qwen3.7 Max is #10 with a score of 72.84.
    Compare
  5. GPT-5.6 Terra
    OpenAI
    #1172.57
    GPT-5.6 Terra is #11 with a score of 72.57.
    Compare
  6. Claude Opus 4.7
    Anthropic
    #1271.94
    Claude Opus 4.7 is #12 with a score of 71.94.
    Compare
  7. Muse Spark
    Meta
    #1371.04
    Muse Spark is #13 with a score of 71.04.
    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. Coding96%
    Eligible cohort rank #6 of 122Category score 71.4
  2. Agentic96%
    Eligible cohort rank #6 of 119Category score 65.8
  3. Knowledge86%
    Eligible cohort rank #8 of 52Category score 83.5
  4. Multimodal64%
    Eligible cohort rank #11 of 29Category score 70.1

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 #6 of 119Percentile 96thWeight 22%24 benchmarksMixed sources65.8
CodingRank #6 of 122Percentile 96thWeight 20%9 benchmarksMixed sources71.4
ReasoningRank Not rankedWeight 17%5 benchmarksMixed sources94.3
KnowledgeRank #8 of 52Percentile 86thWeight 12%10 benchmarksMixed sources83.5
MathRank Not rankedWeight 5%3 benchmarksVerified71.3
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank #11 of 29Percentile 64thWeight 12%5 benchmarksMixed sources70.1
Inst. FollowingWeight 5%1 benchmarkReportedScore pending

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 Overall1481±4.444,927
Coding1519±6.812,460
Math1490±12.62,328
Instruction Following1477±6.514,997
Creative Writing1447±8.27,736
Multi-turn1489±8.17,728
Hard Prompts1500±5.329,190
Hard Prompts (English)1499±6.514,429
Longer Query1485±6.119,765

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.

Agentic24 benchmarks
Terminal-Bench 2.0Benchmark exact
82%Weighted 38%
Source: Terminal-Bench 2.0 leaderboardProvenance: Terminal-Bench reports the public Codex / GPT-5.5 run at 82.0% accuracy.
OSWorld-VerifiedProvider exact
78.7%Weighted 34%
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
BrowseCompProvider exact
84.4%Weighted 28%
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
CyberGymProvider exact
81.8%Display only
Source: OpenAI: Introducing GPT-5.5Provenance: OpenAI reports GPT-5.5 at 81.8% on CyberGym in the launch comparison table.
MCP AtlasProvider exact
75.3%Display only
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
ToolathlonProvider exact
55.6%Display only
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
τ²-bench resultsProvider exact

τ²-Bench Tool-Agent-User Evaluation

93.9%Display only
Source: OpenAI: Introducing GPT-5.5Provenance: OpenAI reports GPT-5.5 at 98.0% on τ²-bench Telecom without prompt tuning and with GPT-4.1 as the user model.
AA Agentic IndexReported

Artificial Analysis Agentic Index

44.9%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.
APEX-Agents-AAReported
37.7%Display only
Source: Artificial Analysis: apex-agents-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
GDPval-AAReported

GDPval-AA normalized

49.5%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.
GDPval-AAReported
1490Display only
Source: Artificial Analysis: gdpval-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Gert LabsBenchmark exact

Gert Labs Composite Game Benchmark

72.93%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.
ResearchClawBenchBenchmark exact
17.0%Display only
Source: ResearchClawBench leaderboardProvenance: ResearchClawBench reports this model as ResearchHarness (GPT-5.5) in the official Pass@1 leaderboard. BenchLM stores the one-decimal RADS average on the local ResearchClawBench display key and excludes it from weighted rankings.
OSWorld 2.0Benchmark exact
13.0%Display only
Source: OSWorld 2.0 paperProvenance: OSWorld 2.0 reports GPT-5.5 batched actions on its 500-step main table. BenchLM stores the binary completion score and notes the corresponding partial score was 49.5%.
JobBenchBenchmark exact
42.7%Display only
Source: JobBench paperProvenance: JobBench reports GPT-5.5 under Codex CLI on the main-set leaderboard. BenchLM stores the reported main-set score.
ExploitGymBenchmark exact
13.4%Display only
Source: ExploitGym paperProvenance: ExploitGym reports GPT-5.5 with Codex CLI produced 120 successful exploits out of 898 tasks. BenchLM stores this as a percentage of the full suite.
AA BriefcaseReported

Artificial Analysis Briefcase

1154Display only
Source: Artificial Analysis: aa-briefcase leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA AutomationBenchReported

Artificial Analysis AutomationBench

42.1%Display only
Source: Artificial Analysis: automationbench-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA EnterpriseOps-GymReported

Artificial Analysis EnterpriseOps-Gym

46.6%Display only
Source: Artificial Analysis: enterprise-ops-gym-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Harvey LABReported

Artificial Analysis Harvey LAB-AA

86.3%Display only
Source: Artificial Analysis: harvey-lab-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA ITBenchReported

Artificial Analysis ITBench-AA

45.8%Display only
Source: Artificial Analysis: itbench-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Tau3 BankingReported

Artificial Analysis Tau3-Banking

31.3%Display only
Source: Artificial Analysis: tau3-banking leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
terminalBenchHardReported
60.6%Display only
Source: Artificial Analysis: terminalbench-hard leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
aaTerminalBench21Reported
84.3%Display only
Source: Artificial Analysis: terminalbench-v2-1 leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Coding9 benchmarks
SWE-bench ProProvider exact
58.6%Weighted 10%
Source: OpenAI: Introducing GPT-5.5Provenance: OpenAI publishes exact GPT-5.5 values for SWE-Bench Pro (Public), Terminal-Bench 2.0, BrowseComp, MCP Atlas, Toolathlon, Tau2-bench Telecom, MMMU Pro, OfficeQA Pro, GPQA Diamond, Humanity's Last Exam, and FrontierMath in the launch evaluation tables.
Terminal-Bench 2.0Benchmark exact
82.0%Display only
Source: Terminal-Bench 2.0 leaderboardProvenance: Terminal-Bench reports the public Codex / GPT-5.5 run at 82.0% accuracy. The same benchmark-native row is used in both coding and agentic category views.
Vibe Code BenchBenchmark exact

Vibe Code Bench v1.1

69.85%Display only
Source: Vals AI: Vibe Code Bench v1.1Provenance: Vals Vibe Code Bench v1.1 reports this exact row under openai/gpt-5.5; BenchLM stores it on the local vibeCodeBench key.
React Native EvalsBenchmark exact
84.7%Display only
Source: React Native Evals leaderboardProvenance: React Native Evals reports this exact overall score for GPT 5.5 in the public dashboard run finished on 2026-04-28.
cursorBench31Benchmark exact
59.2%Display only
Source: Cursor evals: CursorBench 3.1Provenance: Cursor reports GPT-5.5 Medium at this exact CursorBench 3.1 score on its public evals page. BenchLM stores it on the GPT-5.5 row as a display-only coding-agent benchmark.
cursorBench32Benchmark exact
58.4%Display only
Source: Cursor evals: CursorBench 3.2Provenance: Cursor reports GPT-5.5 Extra High at this exact CursorBench 3.2 score on its public evals page. BenchLM stores it on the GPT-5.5 row as a display-only coding-agent benchmark.
AA Coding IndexReported

Artificial Analysis Coding Index

74.9%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-SciCodeReported

Artificial Analysis SciCode

56.1%Display only
Source: Artificial Analysis: scicode leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
FrontierCode 1.1 MainBenchmark exact
43.0%Display only
Source: Cognition: FrontierCode 1.1Provenance: Cognition reports GPT-5.5 at 43.0% on FrontierCode 1.1 Main, using the best xhigh effort row from the published data JSON.
Reasoning5 benchmarks
ARC-AGI-2Provider exact

Abstraction and Reasoning Corpus for AGI v2

85%Weighted 31%
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
MRCR v2 64K-128KProvider exact

OpenAI MRCR v2 8-needle 64K-128K

83.1%Display only
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
MRCR v2 128K-256KProvider exact

OpenAI MRCR v2 8-needle 128K-256K

87.5%Display only
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
AA-LCRReported

Artificial Analysis Long Context Reasoning

74.3%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

27.1%Display only
Source: Artificial Analysis: critpt leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Knowledge10 benchmarks
HLEProvider exact

Humanity's Last Exam

52.2%Weighted 45%
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
GPQAProvider exact

Graduate-Level Google-Proof Q&A

93.6%Weighted 7%
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
GPQA-DProvider exact

GPQA Diamond

93.6%Display only
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
HLE w/o toolsProvider exact

Humanity's Last Exam without tools

41.4%Display only
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
Artificial Analysis Intelligence IndexReported
54.8%Display only
Source: Artificial Analysis: artificial-analysis-intelligence-index leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

93.5%Display only
Source: Artificial Analysis: gpqa-diamond leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

44.3%Display only
Source: Artificial Analysis: humanitys-last-exam leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

20.1%Display only
Source: Artificial Analysis: omniscience leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

56.9%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-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

85.5%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.
Math3 benchmarks
FrontierMath v2 (Tiers 1-3)Benchmark exact

FrontierMath v2 Tiers 1-3

51.700%Weighted 30%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tiers 1-3 at 51.7% for gpt-5.5-pre-release_xhigh. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
FrontierMath v2 (Tier 4)Benchmark exact

FrontierMath v2 Tier 4

35.400%Weighted 10%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tier 4 at 35.4% for gpt-5.5-pre-release_xhigh. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
FrontierMath (legacy)Provider exact

FrontierMath legacy aggregate

51.7%Display only
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
Multimodal5 benchmarks
MMMU-ProProvider exact

Massive Multi-discipline Multimodal Understanding Pro

81.2%Weighted 45%
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
OfficeQA ProProvider exact
54.1%Weighted 30%
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
MMMU-Pro w/ PythonProvider exact

MMMU-Pro with Python

83.2%Display only
Source: OpenAI: Introducing GPT-5.5Provenance: Provider exact
AA-MMMU-ProReported

Artificial Analysis MMMU-Pro

79.9%Display only
Source: Artificial Analysis: mmmu-pro leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Design Arena WebsiteReported

Design Arena Website Elo

1282Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

75.9%Display only
Source: Artificial Analysis: ifbench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.

GPT-5.5 Family

Base entry

Related Earlier Model

GPT-5.4
GPT-5.5 ProScore 63.69

Frequently Asked Questions

How does GPT-5.5 perform overall in AI benchmarks?

GPT-5.5 currently ranks #9 out of 200 models on BenchLM's provisional leaderboard with an overall score of 73.51. It is created by OpenAI. Its published context window is 1M.

Is GPT-5.5 good for knowledge and understanding?

GPT-5.5 ranks #8 out of 52 models in knowledge and understanding benchmarks with an average score of 83.5. It is among the top performers in this category.

Is GPT-5.5 good for coding and programming?

GPT-5.5 ranks #6 out of 122 models in coding and programming benchmarks with an average score of 71.4. It is among the top performers in this category.

Is GPT-5.5 good for mathematics?

GPT-5.5 has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is GPT-5.5 good for reasoning and logic?

GPT-5.5 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is GPT-5.5 good for agentic tool use and computer tasks?

GPT-5.5 ranks #6 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 65.8. It is among the top performers in this category.

Is GPT-5.5 good for multimodal and grounded tasks?

GPT-5.5 ranks #11 out of 29 models in multimodal and grounded tasks benchmarks with an average score of 70.1. There are stronger options in this category.

Is GPT-5.5 good for instruction following?

GPT-5.5 has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Which sibling models are related to GPT-5.5?

GPT-5.5 belongs to the GPT-5.5 family. Related variants on BenchLM include GPT-5.5 Pro.

Does GPT-5.5 have full benchmark coverage on BenchLM?

Not yet. GPT-5.5 currently has 57 published benchmark scores out of the 323 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-5.5?

GPT-5.5 has a published context window of 1M, which determines how much text it can process in a single interaction.

Related Resources

More from OpenAI LLM Pricing Comparison BenchLM Methodology The AI Race Which LLM Should I Use? Benchmark Explainers
Last updated: July 22, 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.