Skip to content
aiqbench

OpenAI · model passport

OpenAI: GPT-5 Nano

gpt-5-nano
  • Cloud only
  • Proprietary licence
  • 400,000 context
  • Released 2025-08-07(curated)
17/27axes covered
Overall · LMArena
1,338#217 of 396
Best percentile
89.7LiveCodeBench (Artificial Analysis)
Cohort standing
48.1median 51.8

What the data says

Benchmarked on 17 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 89.7 pct — LiveCodeBench (Artificial Analysis) (78.9%)

Weakest axes

  • 6.1 pct — SimpleQA Verified (11.7%)
  • 13.6 pct — Terminal-Bench (21.8%)

Uneven: 83.6 percentile points between its best and worst axis — 89.7 pct on LiveCodeBench (Artificial Analysis) versus 6.1 pct on SimpleQA Verified.

  • LiveCodeBench (Artificial Analysis)89.7 pct78.9%Verify →
  • IFBench (Artificial Analysis)78.1 pct67.6%Verify →
  • BFCL v4 (function calling)Dormant board75.6 pct51.5%Verify →
  • MMLU-Pro (Artificial Analysis)59.6 pct78.0%Verify →
  • AIME (math)57.5 pct81.1%Verify →
  • LiveBench54 pct55.0%Verify →
  • GPQA Diamond51.1 pct69.4%Verify →
  • Instruction following47.2 pct1,327Verify →
  • Hard prompts46.7 pct1,356Verify →
  • Coding46.3 pct1,385Verify →
  • Overall45.5 pct1,338Verify →
  • FrontierMath42 pct8.3%Verify →
  • HHEM Hallucination (Vectara)41.9 pct89.5%Verify →
  • Vision Arena30.7 pct1,146Verify →
  • ARC-AGI-225.8 pct2.6%Verify →
  • Terminal-Bench13.6 pct21.8%Verify →
  • SimpleQA Verified6.1 pct11.7%Verify →
  • WebDev ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • SWE-bench VerifiedNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Use it hosted

API model IDopenai/gpt-5-nano
Context length400,000 tokens
Max output128,000 tokens
Acceptstext, image, file
Input price$0.05 per 1M tokens
Cached input price$0.01 per 1M tokens
Output price$0.40 per 1M tokens

API parameters this endpoint supports

Include reasoningMax completion tokensMax tokensReasoningReasoning effortResponse formatSeedStructured outputsTool choiceTool callingVerbosity

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-5-nano","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • gpt-5-nano-high stands at 48.1 (raw mean 47.7) — measured on 17 of 27 axes.

    standingtemplateVerify →

  • gpt-5-nano-high stands at 48.1 versus a cohort median of 51.8 across 146 models released within 180 days — below the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →