OpenAI · proprietary

GPT-4.1

GPT-4.1 by OpenAI appears in 1 source with Reasoning at 21.09. Best read for LLM, Long context, Low cost.

CreatorOpenAI

Release date2025-04-14

Knowledge cutoffNot published

Context1M tokens

Input price$2/M tokens

Output price$8/M tokens

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank61ranking · source_rank

Reasoning21.09reasoning · index_reasoning

Math20.05math · index_math

Coding7.65coding · index_code

Writing10.61writing · index_communication

Vision14.82multimodal · index_vision

Tool calling11.92tool_calling · index_tool_calling

Long context19.25long_context · index_long_context

Finance33.13domain · index_finance

Legal33.2domain · index_legal

Healthcare31.8domain · index_healthcare

GPQA66.3 %reasoning · gpqa_score

AIME 202546.4 %math · aime_2025_score

SWE-bench Verified54.6 %coding · swe_bench_verified_score

Code Arena841.38 %coding · coding_arena_score

Humanity Last Exam5.4 %reasoning · hle_score

MMMLU87.3 %reasoning · mmmlu_score

MMMU74.8 %multimodal · mmmu_score

TAU2 Retail68 %agent · tau_bench_retail_score

CharXiv-R56.7 %multimodal · charxiv_r_score

Context1,047,576 tokenscontext · context

Speed46.37 c/sperformance · throughput

Latency1,089.78 msperformance · latency

Input price2 $/Mpricing · input_price

Output price8 $/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 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.