OpenAI · proprietary

GPT-5.4 nano

GPT-5.4 nano by OpenAI appears in 1 source with Reasoning at 39.89. Best read for LLM, Low cost, Multimodal.

CreatorOpenAI

Release date2026-03-17

Knowledge cutoffNot published

Context400K tokens

Input price$0.2/M tokens

Output price$1.25/M tokens

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank67ranking · source_rank

Reasoning39.89reasoning · index_reasoning

Math32.87math · index_math

Coding23.04coding · index_code

Writing20.84writing · index_communication

Vision22.72multimodal · index_vision

Tool calling15.66tool_calling · index_tool_calling

Long context19.06long_context · index_long_context

Healthcare45.52domain · index_healthcare

GPQA82.8 %reasoning · gpqa_score

Code Arena788.23 %coding · coding_arena_score

Humanity Last Exam24.3 %reasoning · hle_score

MMMU-Pro66.1 %multimodal · mmmu_pro_score

Toolathlon35.5 %tool_calling · toolathlon_score

MCP Atlas56.1 %tool_calling · mcp_atlas_score

MRCR v233.1 %long_context · mrcr_v2_score

SWE-bench Pro52.4 %coding · swe_bench_pro_score

Context400,000 tokenscontext · context

Speed365.38 c/sperformance · throughput

Latency688 msperformance · latency

Input price0.2 $/Mpricing · input_price

Output price1.25 $/Mpricing · output_price

Evidence

Citations and source overlap

LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is GPT-5.4 nano verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.