Translate
Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LiveBench 2.0 LMArena models.dev OpenRouter AIHOT cross-check
Back to leaderboard
OpenAI · Deprecated

GPT-5.4

gpt family · launched 2026-03-05

MultimodalReasoningToolsStructured
AITopic score58.2Not yet ranked

Agent-ready GPT for coding and computer-use workflows at a lower cost

Evidence coverage5%1 evaluations · 1 institutions
Context / maximum output1.1M / 128ktokens
Cache / input / output$0.25 · $2.5 · $15USD per million tokens
Value / freshness40.8 / 58relative value · release freshness
Product profile

What this model supports

Inputtext, image
Outputtext
Knowledge cutoff2025-08-31
WeightsProprietary / hosted
Capability profile

Strengths by domain

Coding—0 public results
Research & reasoning—0 public results
Professional work—0 public results
Knowledge & instruction—0 public results
Behind the score

Every result has a source

Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.

Human preference & indices2 results

AA IndexArtificial Analysis64.97 indexReading 58.2

Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: GPT-5.4Open evidence
Arena TextLMArena1,452.5 EloReading 58.2

Direct LMArena text leaderboard result.

Open evidence
Same builder

More from OpenAI