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
- Cost per task
- ~$0.53/taskest.
Long-tail import from Artificial Analysis (2026-09-24); AA variant: GPT-5.4 nano (xhigh). Price = AA median host price.
Rankings
Coding
Verified#79 / 137rank by quality40.3±8.1quality / 1002/7 benchmarks measuredWriting & chat
Verified#66 / 162rank by quality53.5±4.1quality / 1003/5 benchmarks measuredVision
Verified#66 / 98rank by quality42.9±6.3quality / 1002/6 benchmarks measuredHard reasoning
Verified#83 / 218rank by quality52.3±3.7quality / 1003/4 benchmarks measuredAgents
Verified#76 / 187rank by quality39.0±4.3quality / 1004/7 benchmarks measured
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#12 of 21 (estimated)~74.4%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #11Xing4.0-29B-A4B75.0%
- ~#12GPT-5.4 nanoEstimated74.4%
- #12Flint74.2%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#20 of 24 (estimated)~53.8%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #18Gemini 3.5 Flash-Lite54.2%
- ~#20GPT-5.4 nanoEstimated53.8%
- #20Nemotron 3.5 Super VL51.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#38 of 46 (estimated)~50.2%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #37Qwen3.8 Max (0902)51.0%
- ~#38GPT-5.4 nanoEstimated50.2%
- #38Ripple-65B Preview44.3%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#15 of 28 (estimated)~68.2%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #14Maple-Preview75.1%
- ~#15GPT-5.4 nanoEstimated68.2%
- #15Mistral Small 464.0%
No published score — estimated from related benchmarks
SciCodeVerified
#55 of 11847.2%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #54Intern-S2-397B47.6%
- #55GPT-5.4 nano47.2%
- #56MiniMax-M347.1%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#24 of 26 (estimated)~32.4
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #23Gemini 3.8 Flash33.3
- ~#24GPT-5.4 nanoEstimated32.4
- #24GPT-6 Luna31.1
No published score — estimated from related benchmarks
Writing & chat
LMArena Text, Non-English (Elo)Verified
#42 of 561387 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #41Claude Haiku 4.51395
- #42GPT-5.4 nano1387
- #43Qwen3 Next 80B A3B Instruct1386
lmarena.ai · 2026-09-13
LMArena Text (Elo)Verified
#42 of 561402 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #41Mistral Large 31413
- #42GPT-5.4 nano1402
- #43Qwen3 Next 80B A3B Instruct1399
lmarena.ai · 2026-09-13
EQ-Bench Creative Writing v3 (Elo)Estimated
~#17 of 26 (estimated)~1675 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #16Nemotron 3 Ultra1692
- ~#17GPT-5.4 nanoEstimated1675
- #17Qwen3.8 27B1671
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#53 of 8765.4%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #52DiffusionGemma 26B A4B66.5%
- #53GPT-5.4 nano65.4%
- #54Mistral Medium 3.564.9%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~#11 of 12 (estimated)~75.6%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #10Claude Sonnet 577.0%
- ~#11GPT-5.4 nanoEstimated75.6%
- #11Gemini 3.5 Flash-Lite74.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#5 of 8 (estimated)~81.6%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #4Gemini 3.1 Pro85.3%
- ~#5GPT-5.4 nanoEstimated81.6%
- #5Claude Haiku 4.579.6%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#36 of 477.8%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #35Ling-3.0-flash-VL8.4%
- #36GPT-5.4 nano7.8%
- #37Qwen3.6 35B A3B6.6%
artificialanalysis.ai · 2026-09-24
ChartographyEstimated
~#25 of 25 (estimated)~8.9%
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#73 of 19281.7%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #72K2 Horizon MoVA 36B A4B82.2%
- #73GPT-5.4 nano81.7%
- #74ERNIE 4.5 300B A47B81.1%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#62 of 19828.3%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #61Nemotron 3 Ultra28.4%
- #62GPT-5.4 nano28.3%
- #63GPT-5.4 mini28.1%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#17 of 34 (estimated)~87.3%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #15Ternary Bonsai 27B87.5%
- ~#17GPT-5.4 nanoEstimated87.3%
- #17Bonsai 27B87.1%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#38 of 11976.0%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #37EXAONE 4.5 33B78.1%
- #38GPT-5.4 nano76.0%
- #39Nemotron 3.5 Super VL73.2%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#11 of 15 (estimated)~66.0%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #10Nex-N2.5-Mini71.2%
- ~#11GPT-5.4 nanoEstimated66.0%
- #11Muse 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
~#19 of 22 (estimated)~66.4%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19GPT-5.4 nanoEstimated66.4%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#46 of 91937 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #45Gemini 3.5 Flash-Lite970
- #46GPT-5.4 nano937
- #47Qwen3.6 35B A3B879
artificialanalysis.ai · 2026-09-24
AutomationBench-AAVerified
#50 of 846.0%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #49Mistral Medium 3.56.3%
- #50GPT-5.4 nano6.0%
- #51Qwen3.5 122B A10B5.5%
artificialanalysis.ai · 2026-09-24