OpenAI · proprietary

GPT-5.1

GPT-5.1 by OpenAI appears in 2 sources with Reasoning at 47.52. Best read for Code quality, Coding, High intelligence.

CreatorOpenAI

Release date2025-11-13

Knowledge cutoffNot published

Context400K tokens

Input price$1.25/M tokens

Output price$10/M tokens

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank27ranking · source_rank

Reasoning47.52reasoning · index_reasoning

Math41.36math · index_math

Coding30.81coding · index_code

Research22.22research · index_search

Writing28.3writing · index_communication

Vision34.6multimodal · index_vision

Tool calling24.73tool_calling · index_tool_calling

Healthcare47.52domain · index_healthcare

GPQA88.1 %reasoning · gpqa_score

AIME 202594 %math · aime_2025_score

SWE-bench Verified76.3 %coding · swe_bench_verified_score

Code Arena1,210.49 %coding · coding_arena_score

MMMU85.4 %multimodal · mmmu_score

FrontierMath26.7 %math · frontiermath_score

Context400,000 tokenscontext · context

Speed319.17 c/sperformance · throughput

Latency977.45 msperformance · latency

Input price1.25 $/Mpricing · input_price

Output price10 $/Mpricing · output_price

Arena Rating1,422.51metric

Arena Rank62metric

Vote Count43,500metric

Evidence

Citations and source overlap

Arena AILM Arena text leaderboard (overall) mirrored in the public leaderboard dataset.Retrieved 2026-05-20 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-5.1 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.