GPT-6 Luna

Data updated 31 Oct 2026

21 published benchmark measures · 2 benchmark families contribute across 2 task areas. 2 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

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

AgenticNo 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; 13/13 scenarios unsupported. Without one publisher: No supported estimate; 15/15 unsupported. Smoothing check: No supported estimate; 3/3 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.

Hard reasoning1 families · 1 with independent evidence · Preliminary32.7

1 core families; 59 direct opponents across 10 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; 6/6 scenarios unsupported. Without one publisher: No supported estimate; 16/16 unsupported. Smoothing check: No supported estimate; 3/3 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.

ARC-AGI: 49.2 observed win share
arcprize.org · Source 1

Coding1 families · 1 with independent evidence · Preliminary43.7

1 core families; 21 direct opponents across 7 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; 6/6 scenarios unsupported. Without one publisher: No supported estimate; 19/19 unsupported. Smoothing check: No supported estimate; 3/3 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: 19.0 observed win share
tbench.ai · 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.

MultimodalNo 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; 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 contextNo 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; 5/5 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: 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 · Mixed settings

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.

High: 5 observations
Low: 5 observations
Max: 8 observations
Medium: 5 observations
XHigh: 6 observations
Not specified: 14 observations

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

2 contributing families across 2 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-6
Released: 2026-09-22
Context: 1,050,000 tokens
API list price: $0.10 input / $0.50 output per million tokens
Standard rate for requests up to 272,000 input tokens. Longer requests are priced at 2× input and 1.5× output for the whole request.
License: proprietary
Model card: https://developers.openai.com/api/docs/models/gpt-6-luna
Default Capability family coverage: /badge/gpt-6-luna.svg

Benchmark scores & sources

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

Benchmark	Bucket	Score	Harness	Evidence	Source-recorded date
FrontierCode 1.1	Supporting evidence	41.9269666666667%	Artificial Analysis FrontierCode 1.1 Stirrup Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-10-30
FrontierCode 1.1 Main (score) · 1.1 Main	Supporting evidence	25.66% Reported settings & source Reported reasoning effort low. FrontierCode 1.1 Main, as identified in the surrounding article. The chart title is FrontierCode. Graded on correctness and mergeability. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page. Provider-published lab self-report. Vega-Lite chart data value 0.2566, stored as 25.66 percent. Not an independent board. Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Introducing GPT-6 Sol and Luna · Chart: FrontierCode / GPT-6 Luna / low · reviewed 2026-09-22	Published configuration Effort: Low	lab self-report Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.	Reviewed 2026-09-22
FrontierCode 1.1 Main (score) · 1.1 Main	Supporting evidence	35.53% Reported settings & source Reported reasoning effort medium. FrontierCode 1.1 Main, as identified in the surrounding article. The chart title is FrontierCode. Graded on correctness and mergeability. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page. Provider-published lab self-report. Vega-Lite chart data value 0.3553, stored as 35.53 percent. Not an independent board. Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Introducing GPT-6 Sol and Luna · Chart: FrontierCode / GPT-6 Luna / medium · reviewed 2026-09-22	Published configuration Effort: Medium	lab self-report Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.	Reviewed 2026-09-22
FrontierCode 1.1 Main (score) · 1.1 Main	Supporting evidence	37.26% Reported settings & source Reported reasoning effort high. FrontierCode 1.1 Main, as identified in the surrounding article. The chart title is FrontierCode. Graded on correctness and mergeability. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page. Provider-published lab self-report. Vega-Lite chart data value 0.3726, stored as 37.26 percent. Not an independent board. Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Introducing GPT-6 Sol and Luna · Chart: FrontierCode / GPT-6 Luna / high · reviewed 2026-09-22	Published configuration Effort: High	lab self-report Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.	Reviewed 2026-09-22
FrontierCode 1.1 Main (score) · 1.1 Main	Supporting evidence	37.1% Reported settings & source Reported reasoning effort xhigh. FrontierCode 1.1 Main, as identified in the surrounding article. The chart title is FrontierCode. Graded on correctness and mergeability. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page. Provider-published lab self-report. Vega-Lite chart data value 0.371, stored as 37.1 percent. Not an independent board. Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Introducing GPT-6 Sol and Luna · Chart: FrontierCode / GPT-6 Luna / xhigh · reviewed 2026-09-22	Published configuration Effort: XHigh	lab self-report Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.	Reviewed 2026-09-22
FrontierCode 1.1 Main (score) · 1.1 Main	Supporting evidence	42.42% Reported settings & source Reported reasoning effort max. FrontierCode 1.1 Main, as identified in the surrounding article. The chart title is FrontierCode. Graded on correctness and mergeability. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page. Provider-published lab self-report. Vega-Lite chart data value 0.4242, stored as 42.42 percent. Not an independent board. Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Introducing GPT-6 Sol and Luna · Chart: FrontierCode / GPT-6 Luna / max · reviewed 2026-09-22	Published configuration Effort: Max	lab self-report Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.	Reviewed 2026-09-22
Humanity's Sixth Sense	Supporting evidence	21%	HSS · max Effort: max Reported settings Full 522-task pass@1, task mean of three attempts; every rubric criterion must pass. 95% task-cluster bootstrap CI. Claude-Opus-5 judge. Scale AI + Elorian. Unversioned board; source hashes identify captures. Display only. Excluded from weighted Overall. Source-recorded date is the capture date, not a proven evaluation date.	official board Supporting evidence outside the reviewed capability core	2026-10-31
LMArena Agent Arena	Supporting evidence	2.23	LMArena Agent Arena · max Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-10-28
OSWorld 2.0 (v2026.08.08, offline set, partial score) · 2.0 / v2026.08.08 offline	Agentic	8.26% Reported settings & source Reported reasoning effort low. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page. Provider-published lab self-report. Vega-Lite chart data value 0.0826, stored as 8.26 percent. Not an independent board. Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Luna / low · reviewed 2026-09-22	Published configuration Effort: Low	lab self-report Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.	Reviewed 2026-09-22
OSWorld 2.0 (v2026.08.08, offline set, partial score) · 2.0 / v2026.08.08 offline	Agentic	31.54% Reported settings & source Reported reasoning effort medium. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page. Provider-published lab self-report. Vega-Lite chart data value 0.3154, stored as 31.54 percent. Not an independent board. Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Luna / medium · reviewed 2026-09-22	Published configuration Effort: Medium	lab self-report Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.	Reviewed 2026-09-22
OSWorld 2.0 (v2026.08.08, offline set, partial score) · 2.0 / v2026.08.08 offline	Agentic	41.43% Reported settings & source Reported reasoning effort high. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page. Provider-published lab self-report. Vega-Lite chart data value 0.4143, stored as 41.43 percent. Not an independent board. Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Luna / high · reviewed 2026-09-22	Published configuration Effort: High	lab self-report Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.	Reviewed 2026-09-22
OSWorld 2.0 (v2026.08.08, offline set, partial score) · 2.0 / v2026.08.08 offline	Agentic	46.7% Reported settings & source Reported reasoning effort xhigh. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page. Provider-published lab self-report. Vega-Lite chart data value 0.467, stored as 46.7 percent. Not an independent board. Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Luna / xhigh · reviewed 2026-09-22	Published configuration Effort: XHigh	lab self-report Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.	Reviewed 2026-09-22
OSWorld 2.0 (v2026.08.08, offline set, partial score) · 2.0 / v2026.08.08 offline	Agentic	52.68% Reported settings & source Reported reasoning effort max. Partial reward on the offline set from the v2026.08.08 release. OpenAI-published chart on the Introducing GPT-6 Sol and Luna page. Provider-published lab self-report. Vega-Lite chart data value 0.5268, stored as 52.68 percent. Not an independent board. Comparison limit: Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Introducing GPT-6 Sol and Luna · Chart: OSWorld 2.0, offline set / GPT-6 Luna / max · reviewed 2026-09-22	Published configuration Effort: Max	lab self-report Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.	Reviewed 2026-09-22
Reviewer bypass attempts · Sol 6.1 launch / safety stress test	Supporting evidence	0.26% Reported settings & source Reported reasoning effort max. Attempts to work around an automated safety reviewer blocking an action. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Safety stress outcomes are retained for inspection and excluded from capability scoring. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Comparison limit: Safety failure behavior is not a capability or intelligence score. Introducing GPT-6.1 Sol · Chart: Reviewer bypass attempts (lower is better) / GPT-6 Luna / max · reviewed 2026-09-29	Published configuration Effort: Max	lab self-report Safety failure behavior is not a capability or intelligence score.	Reviewed 2026-09-29
SpireClimb	Supporting evidence	0%	SpireClimb · Slay the Spire 2, Ascension 10 Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-09-28
SpireClimb	Supporting evidence	0%	SpireClimb · Slay the Spire 1, Ascension 20 Heart Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-09-28
Terminal-Bench 4.0	Coding	16.36%	Terminal-Bench 4.0 reported Effort: Not specified contributes to capability	official board	2026-09-22
Warning circumvention · Sol 6.1 launch / safety stress test	Supporting evidence	42.37% Reported settings & source Reported reasoning effort max. Restriction-circumvention attempts in deliberately difficult low-stakes cases without full product safeguards. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Safety stress outcomes are retained for inspection and excluded from capability scoring. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Comparison limit: Safety failure behavior is not a capability or intelligence score. Introducing GPT-6.1 Sol · Chart: Warning circumvention (lower is better) / GPT-6 Luna / max · reviewed 2026-09-29	Published configuration Effort: Max	lab self-report Safety failure behavior is not a capability or intelligence score.	Reviewed 2026-09-29
DeepSWE v1.1	Agentic	—	—	—	—
GDPval-AA	Agentic	—	—	—	—
GPQA Diamond	Hard reasoning	—	—	—	—
Humanity's Last Exam	Hard reasoning	—	—	—	—
LiveCodeBench	Coding	—	—	—	—
LMArena Text Arena	Human pref	—	—	—	—
MMLU-Pro	Knowledge	—	—	—	—