Noometry

OpenAI, proprietary

GPT-5.4 nano

GPT-5.4 nano by OpenAI ranks 125th of 354 ranked models on the Noometry Index as of October 2026, with a score of 41.9. Its strongest category is multimodal, where it ranks 78th. API pricing starts at $0.20 per million input tokens and $1.25 per million output tokens, with a 400K-token context window.

Last verified

Noometry rank
#125 of 354
Index score
41.9
Evidence
Confirmed 40 results
Provider
OpenAI
Released
March 17, 2026
Weights
Proprietary
Reasoning
Yes
Context window
400K
Max output
128K
Input price
$0.20 / M
Output price
$1.25 / M
Blended price
$0.46 / M
Output speed
19 tokens/s Kagi
Value
#71 of 219
Knowledge cutoff
August 2025
Input
text, image

Category scores

Each category score combines every public result we have in that category.

  1. Coding 43.6
  2. Reasoning 23.7
  3. Math 40.9
  4. Knowledge 41.9
  5. Multimodal 36.7
  6. Multilingual 48.6
  7. Instruction Following 71.9
  8. Long Context 41.6
  9. Writing & Preference 55.7
CategoryScoreRankResults
Coding43.6#843
Reasoning23.7#1739
Math40.9#885
Knowledge41.9#1034
Multimodal36.7#781
Multilingual48.6#1401
Instruction Following71.9#1441
Long Context41.6#1371
Writing & Preference55.7#1423

Strengths and weaknesses

Categories where GPT-5.4 nano places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Coding43.6+4.9#84 of 340, top 25%
Math40.9+4.3#88 of 327, top 27%
Knowledge41.9+4.6#103 of 314, top 33%

Weakest categories

CategoryScorevs medianRank
Multimodal36.7−1.8#78 of 128, top 61%
Reasoning23.7+0.1#173 of 350, top 50%
Instruction Following71.9+0.7#144 of 305, top 48%

Closest competitors

The models ranked just above and below GPT-5.4 nano. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Solar Pro4#12142.1$0.52—Compare
GLM-4.5#12242.0$132Compare
Qwen3.5 35B-A3B#12342.0$0.69—Compare
GLM-4.7#12442.0$1—Compare
Amazon Nova Experimental Chat 10 09#12641.9——Compare
Qwen3.5 27B#12741.9$0.82—Compare
GPT-5 Mini#12841.8$0.693Compare
ERNIE 5.0 0110#12941.8——Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
SciCode46.9%#55 of 121, top 46%xhighEpoch AI
WeirdML49.2%#49 of 119, top 42%highEpoch AI
WeirdML38%noneEpoch AI
LMArena Coding1405#134 of 294, top 46%highLMArena2026-10-08
ALE-Bench1,005#42 of 105, top 40%highEpoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
ARC-AGI-23.6%highEpoch AI
ARC-AGI-21.5%lowEpoch AI
ARC-AGI-21.9%mediumEpoch AI
ARC-AGI-25.7%#54 of 83, top 66%xhighEpoch AI
Kagi LLM Benchmark39.7%#80 of 99, top 81%Kagi LLM Benchmark
ARC-AGI-138.2%highEpoch AI
ARC-AGI-118.3%lowEpoch AI
ARC-AGI-133%mediumEpoch AI
ARC-AGI-151.5%#56 of 83, top 68%xhighEpoch AI
CritPt9.3%#49 of 134, top 37%xhighEpoch AI
Chess Puzzles30%#36 of 129, top 28%highEpoch AI2026-04-14
Chess Puzzles17%lowEpoch AI2026-08-07
Chess Puzzles3%noneEpoch AI2026-08-07
LMArena Hard Prompts1381#137 of 297, top 47%highLMArena2026-10-08
Mystery Game Puzzles5%highEpoch AI2026-08-27
Mystery Game Puzzles3%lowEpoch AI2026-08-27
Mystery Game Puzzles6%mediumEpoch AI2026-08-27
Mystery Game Puzzles9%#61 of 74, top 83%noneEpoch AI2026-08-27
DTBench80.3%#73 of 151, top 49%xhighEpoch AI
LMCA36.9%#60 of 125, top 48%xhighEpoch AI
Epoch Capabilities Index145.81#79 of 213, top 38%Epoch AI2026-03-17
ForecastBench57.3#59 of 72, top 82%Epoch AI

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)44.9%#50 of 81, top 62%highEpoch AI2026-06-12
FrontierMath (Tiers 1-3)20.4%lowEpoch AI2026-08-28
FrontierMath (Tiers 1-3)4.6%noneEpoch AI2026-08-28
FrontierMath Tier 412.2%#50 of 63, top 80%highEpoch AI2026-06-12
OTIS Mock AIME 2024-202587.8%#60 of 173, top 35%highEpoch AI2026-04-14
OTIS Mock AIME 2024-202568.9%lowEpoch AI2026-08-07
OTIS Mock AIME 2024-202546.7%noneEpoch AI2026-08-07
ProofBench5%#69 of 77, top 90%highEpoch AI
LMArena Math1406#120 of 285, top 43%highLMArena2026-10-08
FrontierMath (Feb 2025 set)25.9%#24 of 68, top 36%highEpoch AI2026-04-15
FrontierMath Tier 4 (v1)6.3%#23 of 55, top 42%highEpoch AI2026-04-15

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond78.5%#84 of 186, top 46%highEpoch AI2026-04-14
GPQA Diamond72.2%lowEpoch AI2026-08-07
GPQA Diamond55.6%noneEpoch AI2026-08-07
SimpleQA Verified11.7%#73 of 77, top 95%highEpoch AI2026-08-27
Vectara Hallucination Rate (lower is better)3.1%Best of 96Vectara Hallucination Leaderboard
LMArena Expert1396#126 of 273, top 47%highLMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1196#80 of 122, top 66%highLMArena2026-10-09

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1359#140 of 297, top 48%highLMArena2026-10-08
LMArena Chinese1392#142 of 285, top 50%highLMArena2026-10-08
LMArena French1396#123 of 223, top 56%highLMArena2026-10-08
LMArena German1367#118 of 231, top 52%highLMArena2026-10-08
LMArena Japanese1343#102 of 211, top 49%highLMArena2026-10-08
LMArena Korean1320#119 of 213, top 56%highLMArena2026-10-08
LMArena Russian1363#139 of 283, top 50%highLMArena2026-10-08
LMArena Spanish1371#133 of 226, top 59%highLMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1362#138 of 298, top 47%highLMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1366#144 of 291, top 50%highLMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1372#143 of 297, top 49%highLMArena2026-10-08
LMArena Creative Writing1314#160 of 295, top 55%highLMArena2026-10-08
LMArena Multi-Turn1382#133 of 295, top 46%highLMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
azure$0.20$1.25$0.022026-10-10
openai$0.20$1.25$0.022026-10-10
openrouter$0.20$1.25$0.022026-10-10

All OpenAI API prices → Estimate your cost →

Compare GPT-5.4 nano

Other OpenAI models

Frequently asked questions

How good is GPT-5.4 nano?

GPT-5.4 nano by OpenAI ranks 125th of 354 ranked models on the Noometry Index as of October 2026, with a score of 41.9. Its strongest category is multimodal, where it ranks 78th. API pricing starts at $0.20 per million input tokens and $1.25 per million output tokens, with a 400K-token context window.

How much does GPT-5.4 nano cost?

GPT-5.4 nano costs $0.20 per million input tokens and $1.25 per million output tokens on OpenAI's own API, with cached input at $0.02.

What is GPT-5.4 nano's context window?

GPT-5.4 nano accepts up to 400K tokens of input and can write up to 128K tokens in one response.

Is GPT-5.4 nano open source?

No. GPT-5.4 nano is proprietary and available only through OpenAI's API and partner platforms.

How fast is GPT-5.4 nano?

GPT-5.4 nano generated about 19 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

What are GPT-5.4 nano's strengths and weaknesses?

Relative to other ranked models, GPT-5.4 nano places best in coding, math, knowledge and lowest in multimodal, reasoning, instruction following.

What is GPT-5.4 nano best at?

Its best category is multimodal, where it ranks 78th on Noometry.