GPT-5

Data updated 12 Sept 2026

18 published benchmark measures · 12 benchmark families contribute across 5 task areas. 3 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →

Model evidence summary

Choose a configuration

A model-wide score would mix effort settings. This page summarizes published evidence; only identified configurations receive leaderboard ranks.

Compare measured configurations →

The capability chart summarizes evidence across reported settings, not a runnable configuration or a leaderboard rank.

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.

Agentic2 families · 0 with independent evidence · Supported0.9

2 core families; 11 direct opponents across 4 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: 0.2–9.1; 2/11 scenarios unsupported. Without one publisher: 0.2–14.0; 1/15 unsupported. Smoothing check: 0.1–6.6; 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.

Bfcl V4: 77.3 observed win share
Amazon · Source 1
MCP-Atlas: 100.0 observed win share
Amazon · Source 1

Hard reasoning3 families · 1 with independent evidence · Supported33.8

3 core families; 54 direct opponents across 11 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: 20.7–48.0; 0/7 scenarios unsupported. Without one publisher: 23.7–48.0; 1/16 unsupported. Smoothing check: 23.3–42.9; 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.

ARC-AGI: 42.6 observed win share
arcprize.org · Source 1
Aime: 100.0 observed win share
Amazon · Source 1
GPQA: 81.8 observed win share
Amazon · Source 1

Coding3 families · 0 with independent evidence · Supported2.5

3 core families; 9 direct opponents across 4 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: 0.6–14.9; 1/7 scenarios unsupported. Without one publisher: 1.2–12.1; 1/20 unsupported. Smoothing check: 1.1–7.6; 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.

LiveCodeBench: 88.9 observed win share
Amazon · Source 1
SWE-bench Verified: 66.7 observed win share
Amazon · Source 1
Terminal-Bench: 61.1 observed win share
Amazon · 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.

Knowledge1 families · 0 with independent evidence · PreliminaryUnknown

1 core families; 11 direct opponents across 4 labs. No connected comparison to the complete reference panel

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.

MMLU-Pro: 90.9 observed win share
Amazon · Source 1

Multimodal3 families · 0 with independent evidence · PreliminaryUnknown

3 core families; 11 direct opponents across 4 labs. No connected comparison to the complete reference panel

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.

Ocrbench V2 Average Accuracy: 54.5 observed win share
Amazon · Source 1
Mmmu Pro: 100.0 observed win share
Amazon · Source 1
ScreenSpot: 33.3 observed win share
Amazon · Source 1

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.

Compare 5 effort levels across 23 benchmark/harness combinations →

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.

Not specified: 18 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

Compare capability profiles →

Score contributions and missing evidence

12 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: deprecated · Retirement 2026-12-11
Availability: Public provider catalog; account and region restrictions may apply
Family: gpt-5
Released: —
Context: —
License: proprietary
Model card: https://developers.openai.com/api/docs/models/all
Default Capability family coverage: /badge/gpt-5.svg

Benchmark scores & sources

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

Benchmark	Bucket	Score	Harness	Evidence	Source-recorded date
AIME 2025 · source release snapshot; version not specified	Hard reasoning	94.6% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table1 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
ARC-AGI-2	Hard reasoning	9.9%	ARC Prize verified Effort: Not specified contributes to capability	official board	2025-08-07
BFCL v4 · source release snapshot; version not specified	Agentic	61.6% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table2 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
GPQA Diamond · source release snapshot; version not specified	Hard reasoning	85.7% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table1 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
IFBench prompt loose · source release snapshot; version not specified	Supporting evidence	73.1% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table1 · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
LiveCodeBench v5 July2024-January2025 · source release snapshot; version not specified	Coding	84.6% Reported settings & source Nova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
MCPAtlas · source release snapshot; version not specified	Agentic	44.5% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table2 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
MMLU-Pro · source release snapshot; version not specified	Knowledge	87.1% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table1 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
MMMU-Pro · source release snapshot; version not specified	Multimodal	78.4% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table3 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
MultiChallenge · source release snapshot; version not specified	Supporting evidence	69.6% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table1 · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
OCRBench v2 average accuracy · source release snapshot; version not specified	Multimodal	58.1% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table3 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
RealKIE-FCC Verified ALNS · source release snapshot; version not specified	Supporting evidence	51.9% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table3 · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
ScreenSpot point accuracy · source release snapshot; version not specified	Multimodal	31% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table3 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
SWE-bench Verified · source release snapshot; version not specified	Coding	72.8% Reported settings & source Nova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
tau2 Airline Verified · source release snapshot; version not specified	Supporting evidence	72% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table2 · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
tau2 Retail Verified · source release snapshot; version not specified	Supporting evidence	78.3% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table2 · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
tau2 Telecom · source release snapshot; version not specified	Supporting evidence	86.5% Reported settings & source Nova2 launch evaluation; benchmark-specific settings in report. tau2 Verified avg@3; telecom cited AA because user model sensitivity; comparators mix own runs and cited provider scores. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table2 · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
Terminal-Bench 1.0 · 1.0	Coding	41.3% Reported settings & source Nova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
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	—	—	—	—
OSWorld-Verified	Agentic	—	—	—	—
SWE-bench Pro	Agentic	—	—	—	—
SWE-bench Verified	Agentic	—	—	—	—
Terminal-Bench 2.1	Agentic	—	—	—	—