RankingGPT-5.6 Luna

GPT-5.6 Luna

Compare models

Data updated 31 Oct 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.

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

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: 30.7 · SupportedGPT-5.6 Luna · Coding: 45.4 · 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 · Supported30.7

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: 18.1–35.6; 0/6 scenarios unsupported. Without one publisher: 29.7–31.5; 1/16 unsupported. Smoothing check: 28.2–35.5; 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 · Supported45.4

3 core families; 35 direct opponents across 9 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: 38.0–56.9; 0/6 scenarios unsupported. Without one publisher: 42.8–50.9; 0/19 unsupported. Smoothing check: 44.0–47.0; 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: 23.8 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
      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

      2026-10-28
      DAYJOB HealthcareSupporting evidence1.6%DAYJOB Healthcare · max

      Effort: Not specified

      official board

      Supporting evidence outside the reviewed capability core

      2026-10-28
      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