All models

#107 GPT-5.4 Pro

OpenAI · gpt-5.4-pro

Released: · Source

GPT-5.4 Pro is a model from OpenAI. Exact version: gpt-5.4-pro. See the source for capabilities and limitations.

Use cases
Coding, Image understanding, Reasoning, Text
Accepts
Text & code, Images
Produces
Text & code
Context
1050000 tokens

Access

OpenAI · API Computing: Cloud

Price USD

No verified data

Evaluator & score

Composite index · published model-group index · 20.09.2026 · Higher is better

Snapshot: 2026-09-20 · 90% CI [156.73, 161.7]

Official Epoch AI index; combines own, third-party and developer-reported results. It is not a safety audit or a media-generation score.

Conditions

Epoch Capabilities Index; official model-group estimates

Official ECI model scores, Epoch AI, CC BY 4.0. Composite of own, third-party and developer-reported results. 90% bootstrap interval. Not a per-effort score; export date is the model release date, not measurement date. Methodology: https://epoch.ai/eci#documentation

Independent run · xhigh · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

Chess Puzzles; Epoch AI own run; best score across scorers

Epoch AI own run; Chess Puzzles; version: gpt-5.4-pro-2026-03-05_xhigh; mode: xhigh; source id: gpt-5-4-pro-chess-cloud-run; file: chess_puzzles.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 19.03.2026

Independent run · xhigh · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

FrontierMath; Epoch AI own run; best score across scorers

Epoch AI own run; FrontierMath-2025-02-28-Private; version: gpt-5.4-pro-2026-03-05_xhigh; mode: xhigh; source id: pre-release-gpt-5-4-pro-fm-t13; file: frontiermath.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 06.03.2026

Independent run · xhigh · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

FrontierMath-Tier-4-v2-Private; Epoch AI own run; best score across scorers

Epoch AI own run; FrontierMath-Tier-4-v2-Private; version: gpt-5.4-pro-2026-03-05_xhigh; mode: xhigh; source id: W6b3C8AeNC7CAFs5DQma8N; file: frontiermath_tier_4_v2.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 13.06.2026

Independent run · xhigh · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

FrontierMath-Tiers-1-3-v2-Private; Epoch AI own run; best score across scorers

Epoch AI own run; FrontierMath-Tiers-1-3-v2-Private; version: gpt-5.4-pro-2026-03-05_xhigh; mode: xhigh; source id: ZFVa8dw7oiir6PhcF8XZMo; file: frontiermath_tiers_1_3_v2.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 13.06.2026

Independent run · xhigh · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

GPQA Diamond; Epoch AI own run; best score across scorers

Epoch AI own run; GPQA diamond; version: gpt-5.4-pro-2026-03-05_xhigh; mode: xhigh; source id: gpt-5-4-pro-gpqa-cloud-run; file: gpqa_diamond.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 20.03.2026

Independent run · xhigh · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

SimpleQA Verified; Epoch AI own run; best score across scorers

Epoch AI own run; SimpleQA Verified; version: gpt-5.4-pro-2026-03-05_xhigh; mode: xhigh; source id: RfSJbuuuMkeVHQj7xrth4u; file: simpleqa_verified.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 27.08.2026

SourceVerified 20.09.2026