RankingGPT-5.6 Luna

GPT-5.6 Luna

Compare models

Data updated 22 Nov 2026

GPT-5.6 Luna by OpenAI is a GPT-5.6 model. This profile collects the published benchmark results and reported effort settings for this model. Configurations are compared on the effort page. Ranks are on the leaderboard.

51 published benchmark measures · 176 measured effort results · 15 benchmark families contribute across 5 task areas. 5 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →

Compare with

Choose a second model and its effort to see both profiles and benchmark differences below.

Compare with

Choose a configuration to compare. The overview below combines evidence across settings and has no model-wide rank.

Model evidence summary

This profile combines published settings. It is not a runnable configuration or a leaderboard rank. Compare measured configurations →

Performance profile

Capabilities

Adjusted comparison score · 0–100
GPT-5.6 Luna capability radarComparison scores from 0 to 100. Unknown capabilities have no point; lines stop at gaps. Hollow points are preliminary. Exact values and support labels follow the chart.AgenticHard reasoningCodingHuman prefKnowledgeMultimodalLong context50100GPT-5.6 Luna · Agentic: 24.7 · SupportedGPT-5.6 Luna · Hard reasoning: 30.1 · SupportedGPT-5.6 Luna · Coding: 45.9 · SupportedGPT-5.6 Luna · Multimodal: 13.9 · PreliminaryGPT-5.6 Luna · Long context: 44.1 · Supported

Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.

Agentic6 families · 0 with independent evidence · Supported24.7

6 core families; 7 direct opponents across 3 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 20.4–31.6; 0/13 scenarios unsupported. Without one publisher: 20.7–31.1; 1/15 unsupported. Smoothing check: 21.5–31.1; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage; source sensitivity still requires inspection. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

  • Browsecomp: 0.0 observed win share
    OpenAI · Source 1
  • AutomationBench: 33.3 observed win share
    OpenAI · Source 1
  • GDPval: 42.9 observed win share
    OpenAI · Source 1
  • OSWorld: 0.0 observed win share
    OpenAI · Source 1
  • Toolathlon: 33.3 observed win share
    OpenAI · Source 1
  • GDP.pdf: 33.3 observed win share
    OpenAI · Source 1
Hard reasoning3 families · 1 with independent evidence · Supported30.1

3 core families; 59 direct opponents across 10 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 17.8–34.7; 0/6 scenarios unsupported. Without one publisher: 29.2–31.2; 1/16 unsupported. Smoothing check: 27.6–35.1; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Coding3 families · 2 with independent evidence · Supported45.9

3 core families; 40 direct opponents across 10 labs.

Disputed order: matched results across at least two families give the opposite order against 1 peers. Different test mixes and indirect comparisons can cause this. Matched comparison 1

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 38.3–58.3; 0/6 scenarios unsupported. Without one publisher: 43.9–52.4; 0/19 unsupported. Smoothing check: 45.3–46.7; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

  • Terminal-Bench: 27.6 observed win share
    tbench.ai · Source 1
  • DeepSWE: 58.3 observed win share
    OpenAI, deepswe.datacurve.ai · Source 1 Source 2
  • SWE-bench Pro: 33.3 observed win share
    OpenAI · Source 1
Human prefNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 1/1 scenarios unsupported. Without one publisher: No supported estimate; 1/1 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: cross-family and cross-publisher predictions could not be evaluated from the available comparison network. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

    KnowledgeNo comparable evidenceUnknown

    0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

    Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

    Refit without one family: No supported estimate; 4/4 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

    Audit: almost no publisher-held-out comparisons remained estimable. Cross-source validity is unresolved. Validation audit.

    Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

      Multimodal1 families · 0 with independent evidence · Preliminary13.9

      1 core families; 4 direct opponents across 2 labs. Needs broader benchmark and opponent support

      Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

      Refit without one family: No supported estimate; 8/8 scenarios unsupported. Without one publisher: No supported estimate; 8/8 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

      Audit: limited publisher-held-out coverage. Cross-source validity is unresolved. Validation audit.

      Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

      Long context2 families · 0 with independent evidence · Supported44.1

      2 core families; 4 direct opponents across 2 labs.

      Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

      Refit without one family: 44.1–45.0; 2/5 scenarios unsupported. Without one publisher: 44.1–44.1; 2/5 unsupported. Smoothing check: 41.6–47.6; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

      Audit: family and publisher holdouts underperformed neutral predictions. Treat this as an exploratory estimate. Validation audit.

      Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

      Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.

      Reported effort · Not specified

      Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.

      Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.

      Inspect each result and its source ↓ · Download effort evidence
      Score contributions and missing evidence

      15 contributing families across 5 capabilities. Fixed reference panels do not change when the catalog expands.

      Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.

      Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.

      Model information & shareable badge
      Lab
      OpenAI
      Catalog status
      active
      Availability
      Public provider catalog; account and region restrictions may apply
      Family
      GPT-5.6
      Released
      —
      Context
      1,050,000 tokens
      License
      proprietary
      Model card
      https://developers.openai.com/api/docs/models/all
      Default Capability family coverage
      Documented-evidence family coverage/badge/gpt-5.6-luna.svg

      GPT-5.6 Luna measured results by effort setting

      Each row is one published result for one effort setting. Evidence collected 2026-11-22. Compare the effort settings →

      BenchmarkEffortScoreSource
      AA-Briefcase EloHigh1169Artificial Analysis
      AA-Briefcase EloLow740Artificial Analysis
      AA-Briefcase EloMax1339Artificial Analysis
      AA-Briefcase EloMedium933Artificial Analysis
      AA-Briefcase EloNon-reasoning707Artificial Analysis
      AA-Briefcase EloXHigh1267Artificial Analysis
      AA-LCR v1.1High80.3%Artificial Analysis
      AA-LCR v1.1Low70.0%Artificial Analysis
      AA-LCR v1.1Max83.7%Artificial Analysis
      AA-LCR v1.1Medium75.0%Artificial Analysis
      AA-LCR v1.1Non-reasoning42.7%Artificial Analysis
      AA-LCR v1.1XHigh81.7%Artificial Analysis
      AA-Omniscience AccuracyMax39.1%Artificial Analysis
      AA-Omniscience IndexMax-17.1Artificial Analysis
      Agents' Last ExamXHigh30.3%Agents' Last Exam
      APEX-Agents-AAMax35.8%Artificial Analysis
      ARC-AGI-2High29.3%ARC Prize
      ARC-AGI-2Low5.1%ARC Prize
      ARC-AGI-2Max59.5%ARC Prize
      ARC-AGI-2Medium7.4%ARC Prize
      ARC-AGI-2XHigh47.6%ARC Prize
      ARC-AGI-3 · standardHigh0.1%ARC Prize
      ARC-AGI-3 · standardLow0.2%ARC Prize
      ARC-AGI-3 · standardMax0.2%ARC Prize
      ARC-AGI-3 · standardMedium0.2%ARC Prize
      AutomationBench-AAHigh35.6%Artificial Analysis
      AutomationBench-AALow11.7%Artificial Analysis
      AutomationBench-AAMax50.2%Artificial Analysis
      AutomationBench-AAMedium23.1%Artificial Analysis
      AutomationBench-AANon-reasoning5.0%Artificial Analysis
      AutomationBench-AAXHigh42.6%Artificial Analysis
      Bug Hunt BenchMax29.8%Bug Hunt Bench
      CritPtHigh16.6%Artificial Analysis
      CritPtLow2.6%Artificial Analysis
      CritPtMax20.6%Artificial Analysis
      CritPtMedium4.9%Artificial Analysis
      CritPtNon-reasoning0.3%Artificial Analysis
      CritPtXHigh20.6%Artificial Analysis
      DAYJOB FinanceMax1.8%Surge AI
      DAYJOB HealthcareMax0.4%Surge AI
      DeepSWE v1.1High44.2%Datacurve
      DeepSWE v1.1Low1.5%Datacurve
      DeepSWE v1.1Max67.2%Datacurve
      DeepSWE v1.1Medium11.3%Datacurve
      DeepSWE v1.1XHigh56.9%Datacurve
      EnterpriseOps-Gym-AAMax40.8%Artificial Analysis
      Epoch · Chess Puzzles · v2.0.0Low17.0%Epoch AI
      Epoch · Chess Puzzles · v2.0.0Max43.0%Epoch AI
      Epoch · Chess Puzzles · v2.0.0None3.0%Epoch AI
      Epoch · FrontierMath Tier 4 · v2.0.0Max61.0%Epoch AI
      Epoch · FrontierMath Tiers 1–3 · v2.0.0Low41.4%Epoch AI
      Epoch · FrontierMath Tiers 1–3 · v2.0.0Max82.1%Epoch AI
      Epoch · FrontierMath Tiers 1–3 · v2.0.0None39.6%Epoch AI
      Epoch · GPQA diamond · v1.0.11Low82.3%Epoch AI
      Epoch · GPQA diamond · v1.0.11Max91.6%Epoch AI
      Epoch · GPQA diamond · v1.0.11None63.6%Epoch AI
      Epoch · Mystery Game Puzzles · v1.0.4 · Tool submissionLow17.0%Epoch AI
      Epoch · Mystery Game Puzzles · v1.0.4 · Tool submissionMax21.0%Epoch AI
      Epoch · Mystery Game Puzzles · v1.0.4 · Tool submissionMedium12.0%Epoch AI
      Epoch · Mystery Game Puzzles · v1.0.4 · Tool submissionNone20.0%Epoch AI
      Epoch · OTIS Mock AIME 2024-2025 · v1.1.6Low66.7%Epoch AI
      Epoch · OTIS Mock AIME 2024-2025 · v1.1.6Max98.3%Epoch AI
      Epoch · OTIS Mock AIME 2024-2025 · v1.1.6None40.0%Epoch AI
      Epoch · SimpleQA Verified · v1.0.0Max41.0%Epoch AI
      FrontierCode 1.1 · extended-codexHigh50.5%Cognition
      FrontierCode 1.1 · extended-codexLow29.0%Cognition
      FrontierCode 1.1 · extended-codexMax55.1%Cognition
      FrontierCode 1.1 · extended-codexMedium41.2%Cognition
      FrontierCode 1.1 · extended-codexXHigh54.5%Cognition
      FrontierCode 1.1 · main-codexHigh35.9%Cognition
      FrontierCode 1.1 · main-codexLow15.4%Cognition
      FrontierCode 1.1 · main-codexMax39.8%Cognition
      FrontierCode 1.1 · main-codexMedium25.7%Cognition
      FrontierCode 1.1 · main-codexXHigh38.9%Cognition
      GDP.pdf: All-pass RateHigh22.2%Artificial Analysis
      GDP.pdf: All-pass RateLow14.2%Artificial Analysis
      GDP.pdf: All-pass RateMax24.0%Artificial Analysis
      GDP.pdf: All-pass RateMedium15.2%Artificial Analysis
      GDP.pdf: All-pass RateNon-reasoning6.0%Artificial Analysis
      GDP.pdf: All-pass RateXHigh23.8%Artificial Analysis
      GDPval-AA v2.1 LeaderboardHigh1339Artificial Analysis
      GDPval-AA v2.1 LeaderboardLow1002Artificial Analysis
      GDPval-AA v2.1 LeaderboardMax1470Artificial Analysis
      GDPval-AA v2.1 LeaderboardMedium1137Artificial Analysis
      GDPval-AA v2.1 LeaderboardNon-reasoning928Artificial Analysis
      GDPval-AA v2.1 LeaderboardXHigh1407Artificial Analysis
      GPQA DiamondHigh89.2%Artificial Analysis
      GPQA DiamondLow83.5%Artificial Analysis
      GPQA DiamondMax91.1%Artificial Analysis
      GPQA DiamondMedium85.9%Artificial Analysis
      GPQA DiamondNon-reasoning64.5%Artificial Analysis
      GPQA DiamondXHigh89.5%Artificial Analysis
      Humanity's Last ExamHigh33.4%Artificial Analysis
      Humanity's Last ExamLow19.8%Artificial Analysis
      Humanity's Last ExamMax39.5%Artificial Analysis
      Humanity's Last ExamMedium25.8%Artificial Analysis
      Humanity's Last ExamNon-reasoning7.2%Artificial Analysis
      Humanity's Last ExamXHigh37.0%Artificial Analysis
      Humanity's Sixth SenseMax21.6%Scale
      ITBench-AAMax40.3%Artificial Analysis
      LiveBench · AMPS Hard · 2026-06-25Max98.0%LiveBench
      LiveBench · code completion · 2026-06-25Max87.0%LiveBench
      LiveBench · code generation · 2026-06-25Max78.9%LiveBench
      LiveBench · connections · 2026-06-25Max96.5%LiveBench
      LiveBench · consecutive events · 2026-06-25Max86.5%LiveBench
      LiveBench · integrals with game · 2026-06-25Max70.0%LiveBench
      LiveBench · javascript · 2026-06-25Max63.6%LiveBench
      LiveBench · logic with navigation · 2026-06-25Max80.0%LiveBench
      LiveBench · math comp · 2026-06-25Max92.2%LiveBench
      LiveBench · olympiad · 2026-06-25Max88.6%LiveBench
      LiveBench · paraphrase · 2026-06-25Max47.8%LiveBench
      LiveBench · plot unscrambling · 2026-06-25Max51.2%LiveBench
      LiveBench · python · 2026-06-25Max45.0%LiveBench
      LiveBench · simplify · 2026-06-25Max58.7%LiveBench
      LiveBench · spatial · 2026-06-25Max96.0%LiveBench
      LiveBench · story generation · 2026-06-25Max69.1%LiveBench
      LiveBench · summarize · 2026-06-25Max64.9%LiveBench
      LiveBench · tablejoin · 2026-06-25Max47.6%LiveBench
      LiveBench · tablereformat · 2026-06-25Max100.0%LiveBench
      LiveBench · theory of mind · 2026-06-25Max73.1%LiveBench
      LiveBench · typescript · 2026-06-25Max36.7%LiveBench
      LiveBench · typos · 2026-06-25Max70.0%LiveBench
      LiveBench · zebra puzzle · 2026-06-25Max93.5%LiveBench
      LMArena Agent ArenaXHigh-1.2LMArena
      MaxxBenchMax46.1%unLAP
      MLCR-AAHigh16.7%Artificial Analysis
      MLCR-AALow15.6%Artificial Analysis
      MLCR-AAMax20.0%Artificial Analysis
      MLCR-AAMedium13.3%Artificial Analysis
      MLCR-AANon-reasoning8.9%Artificial Analysis
      MLCR-AAXHigh15.0%Artificial Analysis
      MMMU-ProHigh77.6%Artificial Analysis
      MMMU-ProLow74.0%Artificial Analysis
      MMMU-ProMax78.6%Artificial Analysis
      MMMU-ProMedium75.8%Artificial Analysis
      MMMU-ProNon-reasoning60.3%Artificial Analysis
      MMMU-ProXHigh78.6%Artificial Analysis
      SciCodeHigh51.6%Artificial Analysis
      SciCodeLow46.1%Artificial Analysis
      SciCodeMax53.6%Artificial Analysis
      SciCodeMedium46.8%Artificial Analysis
      SciCodeNon-reasoning40.4%Artificial Analysis
      SciCodeXHigh50.5%Artificial Analysis
      SWE-rebench · 2026-06 · toolsMedium31.0%SWE-rebench
      SWE-sweepHigh1.4%SWE-sweep
      SWE-sweepUnspecified0.5%SWE-sweep
      SWE-sweepXHigh2.5%SWE-sweep
      Terminal-Bench 2.1Max75.7%Terminal-Bench
      Terminal-Bench 4.0 · codexMax17.3%Terminal-Bench
      Terminal-Bench v2.1High69.7%Artificial Analysis
      Terminal-Bench v2.1Low43.4%Artificial Analysis
      Terminal-Bench v2.1Max80.9%Artificial Analysis
      Terminal-Bench v2.1Medium53.2%Artificial Analysis
      Terminal-Bench v2.1Non-reasoning39.0%Artificial Analysis
      Terminal-Bench v2.1XHigh77.9%Artificial Analysis
      Terminal-Bench v4.0High2.5%Artificial Analysis
      Terminal-Bench v4.0Low0.0%Artificial Analysis
      Terminal-Bench v4.0Max11.6%Artificial Analysis
      Terminal-Bench v4.0Medium0.5%Artificial Analysis
      Terminal-Bench v4.0Non-reasoning1.0%Artificial Analysis
      Terminal-Bench v4.0XHigh3.5%Artificial Analysis
      Terminal-Bench-Science 0.1Max3.3%Artificial Analysis
      Vals AI · Code Migration v1Max44.5%Vals AI
      Vals AI · Excel Modeling Benchmark v1Max67.1%Vals AI
      Vals AI · Finance Agent v2Max55.0%Vals AI
      Vals AI · Legal Research Bench v1Max36.5%Vals AI
      Vals AI · MMLU-Pro v1Max86.0%Vals AI
      Vals AI · Tax Agent Bench v1: Weighted PassMax60.8%Vals AI
      Vals AI · Terminal-Bench 2.1Max79.0%Vals AI
      Vals AI · Vibe Code Bench v1.1Max77.1%Vals AI
      𝜏³-BankingHigh25.2%Artificial Analysis
      𝜏³-BankingLow12.8%Artificial Analysis
      𝜏³-BankingMax31.1%Artificial Analysis
      𝜏³-BankingMedium17.7%Artificial Analysis
      𝜏³-BankingNon-reasoning9.7%Artificial Analysis
      𝜏³-BankingXHigh28.7%Artificial Analysis
      Benchmark scores & sources

      Original results, evaluation harnesses, and evidence behind this model.

      BenchmarkBucketScoreHarnessEvidenceSource-recorded date
      Agents' Last ExamSupporting evidence30.3%Agents' Last Exam · Codex

      Effort: Not specified

      official board

      Supporting evidence outside the reviewed capability core

      2026-10-20
      Agents' Last Exam · not specifiedSupporting evidence50.3%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Professional table / Agents' Last Exam / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      lab self-report

      Supporting evidence outside the reviewed capability core

      Reviewed 2026-09-06
      ARC-AGI-2Hard reasoning59.5%ARC Prize verified

      Effort: Not specified

      contributes to capability
      official board2026-07-09
      ARC-AGI-3 · 3Hard reasoning0.18%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Abstract Reasoning table / ARC-AGI-3 / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      contributes to capability
      lab self-reportReviewed 2026-09-06
      Artificial Analysis Coding Agent Index v1.1 · v1.1Supporting evidence74.6 index score
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Coding table / Artificial Analysis Coding Agent Index v1.1 / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      lab self-report

      Composite index or publisher-specific internal evaluation lacks a stable general-capability comparison unit.

      Reviewed 2026-09-06
      Artificial Analysis Intelligence Index v4.1 · v4.1Supporting evidence51.2 index score
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Professional table / Artificial Analysis Intelligence Index v4.1 / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      lab self-report

      Composite index or publisher-specific internal evaluation lacks a stable general-capability comparison unit.

      Reviewed 2026-09-06
      AutomationBench · not specifiedAgentic14.9%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Tool Use table / AutomationBench / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      contributes to capability
      lab self-reportReviewed 2026-09-06
      BenchCAD · not specifiedSupporting evidence63.1%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Computer Use table / BenchCAD / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      lab self-report

      Supporting evidence outside the reviewed capability core

      Reviewed 2026-09-06
      BenchCAD (python tool) · not specifiedSupporting evidence73.9%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified; Python tool enabled

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Computer Use table / BenchCAD (python tool) / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      lab self-report

      Supporting evidence outside the reviewed capability core

      Reviewed 2026-09-06
      Big Finance Bench · not specifiedSupporting evidence36%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Professional table / Big Finance Bench / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      lab self-report

      Supporting evidence outside the reviewed capability core

      Reviewed 2026-09-06
      BrowseComp · not specifiedAgentic83.3%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Computer Use table / BrowseComp / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      contributes to capability
      lab self-reportReviewed 2026-09-06
      Bug Hunt BenchSupporting evidence29.81%Bug Hunt Bench · max

      Effort: Not specified

      official board

      Supporting evidence outside the reviewed capability core

      2026-09-22
      Capture-the-Flag Challenges · not specifiedSupporting evidence85.2%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified; reduced or absent production safeguards

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Cybersecurity table / Capture-the-Flag Challenges / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      lab self-report

      Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.

      Reviewed 2026-09-06
      DAYJOB FinanceSupporting evidence4.3%DAYJOB Finance · max

      Effort: Not specified

      official board

      Supporting evidence outside the reviewed capability core

      2026-11-20
      DAYJOB HealthcareSupporting evidence1.6%DAYJOB Healthcare · max

      Effort: Not specified

      official board

      Supporting evidence outside the reviewed capability core

      2026-11-20
      DeepSWE v1.1Coding67.2%DeepSWE v1.1 reported

      Effort: Not specified

      contributes to capability
      official board2026-09-22
      DeepSWE v1.1 · v1.1Coding67.2%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Coding table / DeepSWE v1.1 / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      contributes to capability
      lab self-reportReviewed 2026-09-06
      ExploitBench · not specifiedSupporting evidence33.2%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified; reduced or absent production safeguards; ExploitBench API harness; five seeds; reasoning continuity

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Cybersecurity table / ExploitBench / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      lab self-report

      Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.

      Reviewed 2026-09-06
      ExploitGym · not specifiedSupporting evidence12.4%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified; reduced or absent production safeguards; six-hour evaluation cap; alpha API latency rescaled to public API

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Cybersecurity table / ExploitGym / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      lab self-report

      Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.

      Reviewed 2026-09-06
      FrontierMath Tier 1-3 (v2) · v2Hard reasoning78.6%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Academic table / FrontierMath Tier 1-3 (v2) / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      contributes to capability
      lab self-reportReviewed 2026-09-06
      FrontierMath Tier 4 (v2) · v2Hard reasoning58.5%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Academic table / FrontierMath Tier 4 (v2) / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      contributes to capability
      lab self-reportReviewed 2026-09-06
      gdp.pdf · not specifiedAgentic22.7%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Multimodal table / gdp.pdf / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      contributes to capability
      lab self-reportReviewed 2026-09-06
      GDPval-AA v2 · v2Agentic1592
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Professional table / GDPval-AA v2 / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      contributes to capability
      lab self-reportReviewed 2026-09-06
      GeneBench Pro · not specifiedSupporting evidence10.8%
      Reported settings & source

      Launch table reported configuration; per-cell reasoning effort unspecified

      Provider-published result; comparator measurements are not automatically independently reproduced.

      GPT-5.6: Frontier intelligence that scales with your ambition · Science And Health table / GeneBench Pro / GPT‑5.6 Luna · reviewed 2026-09-06

      Published configuration

      Effort: Not specified

      lab self-report

      Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.

      Reviewed 2026-09-06
      GPQA DiamondHard reasoning91.111%GPQA Diamond reported

      Effort: Not specified

      independent repro

      No matched opponent in this evaluation unit

      2026-09-29