GPT-5.4 nano
- Input
- $0.20/M tok
- Output
- $1.25/M tok
- Blended
- $0.463/M tok · 3:1
- Speed
- 165tok/s
- Context
- 400Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: GPT-5.4 nano (xhigh). Price = AA median host price.
Rankings
Coding
Verified#48 / 103rank by quality38.3±8.0quality / 1002/7 benchmarks measuredWriting & chat
Verified#52 / 146rank by quality55.6±4.2quality / 1003/5 benchmarks measuredVision
Verified#50 / 82rank by quality43.9±6.3quality / 1002/6 benchmarks measuredHard reasoning
Verified#54 / 182rank by quality55.9±3.7quality / 1003/4 benchmarks measuredAgents
Verified#63 / 173rank by quality39.5±4.2quality / 1004/7 benchmarks measured
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#9 of 14 (estimated)~75.7%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #8Muse Glimmer76.0%
- ~#9GPT-5.4 nanoEstimated75.7%
- #9Xing4.0-29B-A4B75.0%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#14 of 19 (estimated)~54.8%
- #1Claude Opus 5.589.9%
- #2Claude Sonnet 5.581.3%
- #13Hy357.9%
- ~#14GPT-5.4 nanoEstimated54.8%
- #14Inkling54.3%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#27 of 31 (estimated)~53.1%
- #1DeepSeek V4.1 Flash74.2%
- #2Grok 4.772.6%
- #26Nex-N2.5-Pro55.8%
- ~#27GPT-5.4 nanoEstimated53.1%
- #27Qwen3.8 Max (0902)51.0%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#8 of 20 (estimated)~73.6%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #7gpt-oss-20b77.7%
- ~#8GPT-5.4 nanoEstimated73.6%
- #8Mistral Small 464.0%
No published score — estimated from related benchmarks
SciCodeVerified
#35 of 9547.2%
- #1Claude Opus 5.566.9%
- #2Claude Fable 5.163.1%
- #34Intern-S2-397B47.6%
- #35GPT-5.4 nano47.2%
- #36MiniMax-M347.1%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~last of 15 (estimated)below measured range (<41.1)
No published score — estimated from related benchmarks
Writing & chat
LMArena Text, Non-English (Elo)Verified
#39 of 531387 Elo
- #1Claude Opus 5.51501
- #2Claude Fable 5.1Few votes1496
- #38Claude Haiku 4.51395
- #39GPT-5.4 nano1387
- #40Qwen3 Next 80B A3B Instruct1386
lmarena.ai · 2026-09-13
LMArena Text (Elo)Verified
#39 of 531402 Elo
- #1Claude Opus 5.51509
- #2Claude Fable 5.11501
- #38Mistral Large 31413
- #39GPT-5.4 nano1402
- #40Qwen3 Next 80B A3B Instruct1399
lmarena.ai · 2026-09-13
EQ-Bench Creative Writing v3 (Elo)Estimated
~#17 of 26 (estimated)~1674 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #16Nemotron 3 Ultra1692
- ~#17GPT-5.4 nanoEstimated1674
- #17Qwen3.8 27B1671
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#43 of 7665.4%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #42DiffusionGemma 26B A4B66.5%
- #43GPT-5.4 nano65.4%
- #44Mistral Medium 3.564.9%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~#8 of 9 (estimated)~75.2%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #7Claude Sonnet 577.0%
- ~#8GPT-5.4 nanoEstimated75.2%
- #8Gemini 3.5 Flash-Lite74.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#5 of 8 (estimated)~81.7%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #4Gemini 3.1 Pro85.3%
- ~#5GPT-5.4 nanoEstimated81.7%
- #5Claude Haiku 4.579.6%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#31 of 427.8%
- #1GPT-6 Astra31.0%
- #2Muse Spark 1.326.6%
- #30Ling-3.0-flash-VL8.4%
- #31GPT-5.4 nano7.8%
- #32Qwen3.6 35B A3B6.6%
artificialanalysis.ai · 2026-09-24
ChartographyEstimated
~#23 of 23 (estimated)~8.9%
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#57 of 17281.7%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #56K2 Horizon MoVA 36B A4B82.2%
- #57GPT-5.4 nano81.7%
- #58ERNIE 4.5 300B A47B81.1%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#47 of 17828.3%
- #1Claude Opus 5.561.4%
- #2Claude Fable 5.159.1%
- #46Nemotron 3 Ultra28.4%
- #47GPT-5.4 nano28.3%
- #48GPT-5.4 mini28.1%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#6 of 25 (estimated)~89.8%
- #1Inkling97.1%
- #2Muse Glimmer94.7%
- #5Xing4.0-29B-A4B90.0%
- ~#6GPT-5.4 nanoEstimated89.8%
- #6gpt-oss-20b89.3%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#36 of 11576.0%
- #1Step 3.7 Flash98.5%
- #2Gemini 3.1 Pro95.6%
- #35EXAONE 4.5 33B78.1%
- #36GPT-5.4 nano76.0%
- #37Nova 2.0 Lite72.8%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#10 of 12 (estimated)~67.7%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #9Nex-N2.5-Mini71.2%
- ~#10GPT-5.4 nanoEstimated67.7%
- #10Muse Glimmer65.9%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompEstimated
~#15 of 18 (estimated)~65.3%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #14Inkling77.1%
- ~#15GPT-5.4 nanoEstimated65.3%
- #15Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#41 of 86937 Elo
- #1Claude Opus 5.51846
- #2Claude Fable 5.11735
- #40Gemini 3.5 Flash-Lite970
- #41GPT-5.4 nano937
- #42Qwen3.6 35B A3B879
artificialanalysis.ai · 2026-09-24
AutomationBench-AAVerified
#45 of 796.0%
- #1Claude Opus 5.569.5%
- #2DeepSeek V4.1 Flash68.9%
- #44Mistral Medium 3.56.3%
- #45GPT-5.4 nano6.0%
- #46Qwen3.5 122B A10B5.5%
artificialanalysis.ai · 2026-09-24