OpenAI · proprietary

GPT-4.1 mini

GPT-4.1 mini by OpenAI appears in 1 source with Reasoning at 15.71. Best read for LLM, Long context, Low cost.

CreatorOpenAI

Release date2025-04-14

Knowledge cutoffNot published

Context1M tokens

Input price$0.4/M tokens

Output price$1.6/M tokens

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank43ranking · source_rank

Reasoning15.71reasoning · index_reasoning

Math16.22math · index_math

Coding-1.49coding · index_code

Writing2.67writing · index_communication

Vision14.22multimodal · index_vision

Tool calling-0.63tool_calling · index_tool_calling

Long context12.32long_context · index_long_context

Finance24.85domain · index_finance

Legal24.91domain · index_legal

Healthcare25.81domain · index_healthcare

GPQA65 %reasoning · gpqa_score

AIME 202540.2 %math · aime_2025_score

SWE-bench Verified23.6 %coding · swe_bench_verified_score

Code Arena1,051.1 %coding · coding_arena_score

Humanity Last Exam3.7 %reasoning · hle_score

MMMLU78.5 %reasoning · mmmlu_score

MMMU72.7 %multimodal · mmmu_score

TAU2 Retail55.8 %agent · tau_bench_retail_score

CharXiv-R56.8 %multimodal · charxiv_r_score

Context1,047,576 tokenscontext · context

Speed26.71 c/sperformance · throughput

Latency927.38 msperformance · latency

Input price0.4 $/Mpricing · input_price

Output price1.6 $/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-4.1 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.