ModelLab
ModelsCompare
ModelsGPT-5.1
OA

GPT-5.1

OpenAI

Previous flagship — now value-priced, still excellent.

FrontierVision
Lab page

Released

Oct 20, 2025

Context

400K

Pricing

$1.50/$6.00

per 1M tok

Best at

Reliable reasoning

Performance

Benchmarks

Chatbot Arena
1458#8/17

Crowdsourced head-to-head chat preference Elo from LMArena. Captures perceived helpfulness and vibe across real-world prompts.

SWE-bench Verified
68.5#6/17

Share of real GitHub issues a model can autonomously resolve end-to-end (with tests passing). The de-facto agentic coding benchmark.

AIME 2025
94.2#5/16

American Invitational Mathematics Examination — competition math that rewards deep, multi-step reasoning. Reported as % solved.

GPQA Diamond
88.0#4/17

Google-proof graduate-level science Q&A (physics, biology, chemistry). PhD-level questions that resist web lookup.

MMLU-Pro
85.1#4/17

Harder, 10-way multiple-choice version of MMLU across 14 academic and professional domains. Breadth-of-knowledge signal.

Aider Polyglot
79.6#6/17

Editing a real codebase across multiple languages. Measures practical, instruction-following coding skill (not just generation).

OSWorld
38.4#5/16

Computer-use / agentic benchmark: completing real desktop OS tasks (apps, files, browsers). The leading autonomy metric.

Value score: 66/100

Quality-per-dollar blend of Chatbot Arena Elo against API price. Free / open models are scored against a floor.

API pricing

Input$1.50per 1M tokens
Output$6.00per 1M tokens
1M tokens blended$7.50in + out

Capabilities

  • Reliable reasoning
  • 400K context
  • Value tier
TextVisionReasoningCode

Closest rivals

By Chatbot Arena Elo

  • DS

    DeepSeek V4

    DeepSeek

    1461
  • G

    Gemini 3 Flash

    Google

    1451
  • ∞

    Llama 4 Behemoth

    Meta

    1469

More from

OpenAI

OA

GPT-5.5

OpenAI's flagship all-rounder with strong computer use.

OA

GPT-5.1 mini

Fast, cheap, capable — the everyday workhorse.

Data last checked Jun 1, 2026 (2mo ago)

ModelLab

An independent dashboard for comparing frontier AI models. Benchmark scores are drawn from public model cards, papers, and leaderboards. Always verify against the original source before making decisions.

Navigate

  • All models
  • Compare
  • About the data

Sources

  • LMArena ↗
  • SWE-bench ↗
  • LiveBench ↗

Data snapshot last checked June 17, 2026.

Not affiliated with any AI lab. Scores are approximations.