OpenAI, released Mar 17, 2026

GPT-5.4 nanoprice, context, benchmarks and release details

100% confidence 100 percent, Full confidence, 5 of 7 expected sources in
57.4
SI Score
#75 of 142 ranked models
Input, per 1M tokens
$0.20models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.4-nano Retrieved Oct 9, 2026 · MIT
Open source ↗
Output, per 1M tokens
$1.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.4-nano Retrieved Oct 9, 2026 · MIT
Open source ↗
Context window
400Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
128Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Mar 17, 2026OpenAI API changelogPublished source fact Retrieved Oct 9, 2026 · factual citation
Open source ↗

How the score breaks down

Coding (weight 40 percent) 55.5
Math (weight 15 percent) 66.1
Preference (weight 15 percent) 70.3
Reasoning (weight 30 percent) 54.9

Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 05:13 UTC.

Around it on the leaderboard

  1. 73 Grok 4.20 (Reasoning) 57.7
  2. 74 MiMo-V2.6-Pro 57.4
  3. 75 GPT-5.4 nano 57.4
  4. 76 GPT-5.4 mini 56.9
  5. 77 LongCat-2.0 56.6

Full leaderboard

Benchmark results

29 benchmarks, 48 results

Each row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.

ARC-AGI-1 (public eval)reasoning 51.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 51.6 4 settings
  • Setting 1 51.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 24.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 43.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 4 47.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-1 (public eval)
ARC-AGI-1 (semi-private)reasoning 51.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 51.5 4 settings
  • Setting 1 38.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 18.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 33%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 4 51.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-1 (semi-private)
ARC-AGI-2 (public eval)reasoning 5.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 5.1 4 settings
  • Setting 1 5.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 3.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 4 4.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-2 (public eval)
ARC-AGI-2 (semi-private)reasoning 5.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 5.7 4 settings
  • Setting 1 3.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 1.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 1.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 4 5.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-nano-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-2 (semi-private)
GPQA Diamondreasoning 82.8%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] reasoning effort xhighPublished Mar 17, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 82.8 4 settings
  • no reasoning 55.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • low effort 72.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 78.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Apr 14, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 4 82.8%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] reasoning effort xhighPublished Mar 17, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
    Open source ↗
About GPQA Diamond
Humanity's Last Examreasoning 24.3%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] without toolsPublished Mar 17, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 24.3
Humanity's Last Exam (with tools)reasoning 37.7%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] with toolsPublished Mar 17, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 37.7
LiveBench Reasoning: connectionsreasoning 94.4%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 94.4
LiveBench Reasoning: consecutive eventsreasoning 54.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 54.3
LiveBench Reasoning: logic with navigationreasoning 64%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 64.0
LiveBench Reasoning: spatialreasoning 82%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 82.0
LiveBench Reasoning: theory of mindreasoning 80.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 80.8
LiveBench Reasoning: zebra puzzlesreasoning 97.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 97.6
FrontierMath Tier 4 (v2)math 12.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jun 12, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 12.2
FrontierMath Tiers 1–3 (v2)math 44.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jun 12, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 44.9 3 settings
  • no reasoning 4.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 28, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • low effort 20.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 28, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 44.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jun 12, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About FrontierMath Tiers 1–3 (v2)
LiveBench Math: AMPS Hardmath 98%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 98.0
LiveBench Math: competition mathmath 95.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 95.1
LiveBench Math: integralsmath 82.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 82.8
LiveBench Math: olympiadmath 88.0%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 88.0
LiveBench Math: simplifymath 62.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 62.8
OTIS Mock AIME 2024–2025math 87.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Apr 14, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 87.8 3 settings
  • no reasoning 46.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • low effort 68.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 87.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Apr 14, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About OTIS Mock AIME 2024–2025
LiveBench Coding: code completioncoding 67.4%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 67.4
LiveBench Coding: code generationcoding 74.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 74.3
LiveBench Coding: JavaScriptcoding 63.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 63.6
LiveBench Coding: Pythoncoding 50%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 50.0
LiveBench Coding: TypeScriptcoding 26.7%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 26.7
SWE-bench Procoding 52.4%Official model cards via models.devLab-reported; metric resolve rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] reasoning effort xhighPublished Mar 17, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 52.4
Terminal-Bench 2.0coding 46.3%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] reasoning effort xhigh; 2.0Published Mar 17, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 46.3
LMArena Textpreference 1372.1 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 70.3

Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.

Details and sources

Open weights
Nomodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
text, imagemodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
First seen by SuperIndex
Oct 8, 2026
Coverage
81% of expected source weight

Reported (5)

  • ARC PrizeOct 8, 2026
  • Epoch AI BenchmarkingOct 8, 2026
  • Official model cards via models.devOct 8, 2026
  • LiveBenchOct 8, 2026
  • LMArena / ArenaOct 8, 2026

Awaiting (2)

  • Humanity’s Last Exam13% of weight
  • Terminal-Bench6% of weight

Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.

What changed

All releases · RSS feed

Alerts on this device

What to be alerted about
RSS feed