#43 GPT-5.4 Nano
medium- Cost
- $0.007
- Time
- 24.6s
- Tokens
- 4,943 tok
OpenAI
Release: 2026-03-17
Tested on: 2026-04-11 01:44
openai/gpt-5.4-nano::medium
~120B total (~5B active)MoEClosedEstimated
(medium)
(none)
Summary
GPT-5.4 Nano scores 7.6 on AI BENCHY and ranks #43. It has N/A reliability, a 68.5% pass rate, $0.083 total cost, and 11.21s average response time.
What makes GPT-5.4 Nano unique: It stands out most in Domain specific, where it ranks #3, while General Intelligence is its weakest area at #18. Its total benchmark cost is unusually low for its score range.
Model facts
Researched on 2026-08-12
- Parameters
- ~120B total (~5B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Vendor does not disclose the architecture or count.
7.6
Consistency
9.0
N/A
$0.083
Total Output Tokens
61,078
Total Input Tokens
0
Input Price
$0.200 / 1M
Output Price
$1.250 / 1M
Flaky tests
2
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 02:18 Re-test | 7.5 | 10.0 | $0.142 | Compare | |
| 2026-07-16 22:36 New test added | 7.5 | 10.0 | $0.138 | Compare | |
| 2026-06-04 13:46 New test added | 7.0 | 10.0 | $0.107 | Compare | |
| 2026-05-22 00:20 Suite changed | 7.1 | 10.0 | $0.099 | Compare | |
| 2026-04-11 01:44 First recorded run | 7.6 | N/A | $0.083 | Current run |
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-04-11 01:44 · First recorded run | 54/54 attempts | 7.6 | 9.0 | N/A | 11/18 | 2 | 61,078 | 0 | $0.083 | 11.21s |
| 2026-06-04 13:46 · New test added | 63/63 attempts | 7.0 | 8.4 | 10.0 | 11/21 | 4 | 79,534 | 35,434 | $0.107 | 11.95s |
| Difference | — | +0.5 | +0.6 | 0 | -2 | -18456 | -35434 | -$0.025 | -740ms |
Benchmark coverage differs: 54/54 attempts (Target: 3 repeats per test) versus 63/63 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
GPT-5.4 NanomediumvsClaude Opus 5noneGPT-5.4 NanomediumvsGPT-5.6 TerralowGPT-5.4 NanomediumvsNemotron 3 UltramediumFree AvailableGPT-5.4 NanomediumvsMiniMax M3mediumGPT-5.4 NanomediumvsSolar Pro 4xhighGPT-5.4 NanomediumvsGPT 5.3 ChatnoneGPT-5.4 NanomediumvsGPT-5.6 LunahighGPT-5.4 NanomediumvsQwen3.5 Plus 2026-02-15mediumGPT-5.4 NanomediumvsDeepSeek V4 Flash 0423highGPT-5.4 NanomediumvsQwen3.5-27Bmedium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 8.3 | 10.0 | |
| Coding | 10.0 | 10.0 | |
| Combined | 9.8 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.9 | 7.2 | |
| General Intelligence | 4.5 | 10.0 | |
| Instructions following | 9.8 | 10.0 | |
| Puzzle Solving | 4.0 | 7.1 | |
| Tool Calling | 10.0 | 10.0 |