OpenAI · proprietary

GPT-5.4 mini

GPT-5.4 mini by OpenAI appears in 1 source with Reasoning at 45.79. Best read for LLM, Low cost, Multimodal.

CreatorOpenAI

Release date2026-03-17

Knowledge cutoffNot published

Context400K tokens

Input price$0.75/M tokens

Output price$4.5/M tokens

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank17ranking · source_rank

Reasoning45.79reasoning · index_reasoning

Math35.73math · index_math

Coding34coding · index_code

Writing22.19writing · index_communication

Vision28.58multimodal · index_vision

Tool calling23.87tool_calling · index_tool_calling

Long context19.84long_context · index_long_context

Healthcare37.74domain · index_healthcare

GPQA88 %reasoning · gpqa_score

Code Arena1,388.34 %coding · coding_arena_score

Humanity Last Exam28.2 %reasoning · hle_score

MMMU-Pro76.6 %multimodal · mmmu_pro_score

Toolathlon42.9 %tool_calling · toolathlon_score

MCP Atlas57.7 %tool_calling · mcp_atlas_score

MRCR v233.6 %long_context · mrcr_v2_score

SWE-bench Pro54.4 %coding · swe_bench_pro_score

Context400,000 tokenscontext · context

Speed283.13 c/sperformance · throughput

Latency608.17 msperformance · latency

Input price0.75 $/Mpricing · input_price

Output price4.5 $/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 mini 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.