Skip to content
Model Wayfinder
← Back to comparison
OpenAI

GPT-4.1

Proprietary – cloud only

Benchmarks

Benchmark average
29/100
based on 6 benchmarks
BenchmarkScorePositionSource
LMArena Text conversation (user votes)1,383 Elo30/ 150LMArena · Nov 11, 2026
LMArena Creative Writing creative writing1,364 Elo39/ 150LMArena · Nov 11, 2026
LMArena Non-English languages1,370 Elo31/ 150LMArena · Nov 11, 2026
LMArena Coding coding1,391 Elo27/ 150LMArena · Nov 11, 2026
LMArena Math maths1,370 Elo24/ 145LMArena · Nov 11, 2026
LMArena Vision image understanding1,210 Elo23/ 85LMArena · Nov 9, 2026

Position: 100 = best, 0 = last among all models listed here that were tested on this benchmark.

Strengths & weaknesses

Automatic summary from benchmark positions – not an opinion.

Pros
    Cons
    • −Weaker in conversation (user votes) (position 30/100)
    • −Weaker in coding (position 27/100)
    • −Weaker in maths (position 24/100)
    • −Weaker in image understanding (position 23/100)

    Our quality rating

    Chatbot (e.g. customer service)2/3
    Writing texts and emails2/3
    Summarising documents2/3
    Translating2/3
    Programming2/3
    Maths & calculations2/3
    Analysing images2/3
    Analysing videos2/3
    Field: Law & public administration2/3
    Field: Medicine & health2/3
    Field: Business & finance2/3
    Field: Science & research2/3

    Tiers derived from: LMArena Text 2026-11-11 · LMArena Creative Writing 2026-11-11 · LMArena Longer Query 2026-11-11 · LMArena Non-English 2026-11-11 · LMArena Coding 2026-11-11 · LMArena Math 2026-11-11 · LMArena Vision 2026-11-09 · LMArena Legal & Government 2026-11-11 · LMArena Medicine & Healthcare 2026-11-11 · LMArena Business & Finance 2026-11-11 · LMArena Science 2026-11-11

    Source, checked Nov 17, 2026