GPT-6 Sol

Data updated 31 Oct 2026

24 published benchmark measures · 7 benchmark families contribute across 3 task areas. 3 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.

Agentic4 families · 0 with independent evidence · Preliminary74.3

4 core families; 2 direct opponents across 1 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; 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.

AutomationBench: 0.0 observed win share
OpenAI · Source 1 Source 2 Source 3 Source 4 Source 5
OSWorld: 0.0 observed win share
OpenAI · Source 1 Source 2 Source 3 Source 4 Source 5
Terminal-Bench Science: 0.0 observed win share
OpenAI · Source 1 Source 2 Source 3 Source 4 Source 5
GDP.pdf: 0.0 observed win share
OpenAI · Source 1 Source 2 Source 3 Source 4 Source 5

Hard reasoning1 families · 1 with independent evidence · Preliminary74.6

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: 88.1 observed win share
arcprize.org · Source 1

Coding2 families · 1 with independent evidence · Preliminary85.1

2 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: 76.2 observed win share
tbench.ai · Source 1
DeepSWE: 0.0 observed win share
OpenAI · Source 1 Source 2 Source 3 Source 4 Source 5

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: 11 observations
Low: 11 observations
Max: 14 observations
Medium: 11 observations
XHigh: 12 observations
Not specified: 15 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

7 contributing families across 3 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: $2 input / $10 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-sol
Default Capability family coverage: /badge/gpt-6-sol.svg

Benchmark scores & sources

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

Benchmark	Bucket	Score	Harness	Evidence	Source-recorded date
gdp.pdf · not specified	Agentic	23.8% Reported settings & source Reported reasoning effort xhigh. Professional questions about complex PDFs across ten professional domains. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Published chart cost per task $0.37; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Introducing GPT-6.1 Sol · Chart: GDP.pdf / GPT-6 Sol / xhigh · reviewed 2026-09-29	Published configuration Effort: XHigh contributes to capability	lab self-report	Reviewed 2026-09-29
gdp.pdf · not specified	Agentic	24.8% Reported settings & source Reported reasoning effort max. Professional questions about complex PDFs across ten professional domains. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Published chart cost per task $0.43; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Introducing GPT-6.1 Sol · Chart: GDP.pdf / GPT-6 Sol / max · reviewed 2026-09-29	Published configuration Effort: Max contributes to capability	lab self-report	Reviewed 2026-09-29
Humanity's Sixth Sense	Supporting evidence	31.2%	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	7.96	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	43.9% 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 0.439, stored as 43.9 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 Sol / 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	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 0.54, stored as 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 Sol / 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	58.29% 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 0.5829, stored as 58.29 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 Sol / 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	60.54% 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 0.6054, stored as 60.54 percent. Not an independent board. Article prose rounds this xhigh point to 60.5%. 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 Sol / 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	64.43% 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 0.6443, stored as 64.43 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 Sol / 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
OSWorld 2.0 (v2026.08.08, offline set, partial score) · 2.0 / v2026.08.08 offline	Agentic	43.9% Reported settings & source Reported reasoning effort low. Offline set from v2026.08.08; partial reward, not binary full-task success or OSWorld Verified. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Published chart cost per task $1.0117; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Introducing GPT-6.1 Sol · Chart: OSWorld 2.0, offline set / GPT-6 Sol / low · reviewed 2026-09-29	Published configuration Effort: Low contributes to capability	lab self-report	Reviewed 2026-09-29
OSWorld 2.0 (v2026.08.08, offline set, partial score) · 2.0 / v2026.08.08 offline	Agentic	54% Reported settings & source Reported reasoning effort medium. Offline set from v2026.08.08; partial reward, not binary full-task success or OSWorld Verified. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Published chart cost per task $1.3789; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Introducing GPT-6.1 Sol · Chart: OSWorld 2.0, offline set / GPT-6 Sol / medium · reviewed 2026-09-29	Published configuration Effort: Medium contributes to capability	lab self-report	Reviewed 2026-09-29
OSWorld 2.0 (v2026.08.08, offline set, partial score) · 2.0 / v2026.08.08 offline	Agentic	58.29% Reported settings & source Reported reasoning effort high. Offline set from v2026.08.08; partial reward, not binary full-task success or OSWorld Verified. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Published chart cost per task $1.7096; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Introducing GPT-6.1 Sol · Chart: OSWorld 2.0, offline set / GPT-6 Sol / high · reviewed 2026-09-29	Published configuration Effort: High contributes to capability	lab self-report	Reviewed 2026-09-29
OSWorld 2.0 (v2026.08.08, offline set, partial score) · 2.0 / v2026.08.08 offline	Agentic	60.54% Reported settings & source Reported reasoning effort xhigh. Offline set from v2026.08.08; partial reward, not binary full-task success or OSWorld Verified. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Published chart cost per task $2.3002; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Introducing GPT-6.1 Sol · Chart: OSWorld 2.0, offline set / GPT-6 Sol / xhigh · reviewed 2026-09-29	Published configuration Effort: XHigh contributes to capability	lab self-report	Reviewed 2026-09-29
OSWorld 2.0 (v2026.08.08, offline set, partial score) · 2.0 / v2026.08.08 offline	Agentic	64.43% Reported settings & source Reported reasoning effort max. Offline set from v2026.08.08; partial reward, not binary full-task success or OSWorld Verified. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Published chart cost per task $3.3695; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Introducing GPT-6.1 Sol · Chart: OSWorld 2.0, offline set / GPT-6 Sol / max · reviewed 2026-09-29	Published configuration Effort: Max contributes to capability	lab self-report	Reviewed 2026-09-29
Reviewer bypass attempts · Sol 6.1 launch / safety stress test	Supporting evidence	0% 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 Sol / 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	13%	SpireClimb · Slay the Spire 2, Ascension 10 Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-09-22
SpireClimb	Supporting evidence	2%	SpireClimb · Slay the Spire 1, Ascension 20 Heart Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-09-24
Terminal-Bench 4.0	Coding	49.39%	Terminal-Bench 4.0 reported Effort: Not specified contributes to capability	official board	2026-09-22
Terminal-Bench Science 0.1 · 0.1	Agentic	9.17% Reported settings & source Reported reasoning effort low. Scientific research workflows using code and terminal tools, including analysis, simulation and model fitting. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Published chart cost per task $2.9986; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Introducing GPT-6.1 Sol · Chart: Terminal-Bench Science 0.1 / GPT-6 Sol / low · reviewed 2026-09-29	Published configuration Effort: Low contributes to capability	lab self-report	Reviewed 2026-09-29
Terminal-Bench Science 0.1 · 0.1	Agentic	14.49% Reported settings & source Reported reasoning effort medium. Scientific research workflows using code and terminal tools, including analysis, simulation and model fitting. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Published chart cost per task $4.4068; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Introducing GPT-6.1 Sol · Chart: Terminal-Bench Science 0.1 / GPT-6 Sol / medium · reviewed 2026-09-29	Published configuration Effort: Medium contributes to capability	lab self-report	Reviewed 2026-09-29
Terminal-Bench Science 0.1 · 0.1	Agentic	14.61% Reported settings & source Reported reasoning effort high. Scientific research workflows using code and terminal tools, including analysis, simulation and model fitting. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Published chart cost per task $4.6325; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Introducing GPT-6.1 Sol · Chart: Terminal-Bench Science 0.1 / GPT-6 Sol / high · reviewed 2026-09-29	Published configuration Effort: High contributes to capability	lab self-report	Reviewed 2026-09-29
Terminal-Bench Science 0.1 · 0.1	Agentic	25.29% Reported settings & source Reported reasoning effort xhigh. Scientific research workflows using code and terminal tools, including analysis, simulation and model fitting. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Published chart cost per task $6.7698; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Introducing GPT-6.1 Sol · Chart: Terminal-Bench Science 0.1 / GPT-6 Sol / xhigh · reviewed 2026-09-29	Published configuration Effort: XHigh contributes to capability	lab self-report	Reviewed 2026-09-29
Terminal-Bench Science 0.1 · 0.1	Agentic	27.59% Reported settings & source Reported reasoning effort max. Scientific research workflows using code and terminal tools, including analysis, simulation and model fitting. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Published chart cost per task $12.1803; source-specific cost does not establish consensus workload efficiency. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Introducing GPT-6.1 Sol · Chart: Terminal-Bench Science 0.1 / GPT-6 Sol / max · reviewed 2026-09-29	Published configuration Effort: Max contributes to capability	lab self-report	Reviewed 2026-09-29
Warning circumvention · Sol 6.1 launch / safety stress test	Supporting evidence	64.39% 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 Sol / 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	—	—	—	—