#136 GPT-5.4 Mini
none- Cost
- $0.010
- Time
- 11.7s
- Tokens
- 2,151 tok
OpenAI
Release: 2026-03-17
Tested on: 2026-05-22 00:18
openai/gpt-5.4-mini::none
~400B total (~17B active)MoEClosedEstimated
(medium)
(none)
Summary
GPT-5.4 Mini scores 4.9 on AI BENCHY and ranks #136. It has 10.0 reliability, a 31.7% pass rate, $0.035 total cost, and 1.16s average response time.
What makes GPT-5.4 Mini unique: Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.
Model facts
Researched on 2026-08-12
- Parameters
- ~400B total (~17B 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.
4.9
Consistency
8.8
10.0
$0.035
Total Output Tokens
2,496
Total Input Tokens
0
Input Price
$0.750 / 1M
Output Price
$4.500 / 1M
Flaky tests
3
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 02:16 Re-test | 5.9 | 10.0 | $0.095 | Compare | |
| 2026-07-16 22:33 New test added | 5.9 | 10.0 | $0.095 | Compare | |
| 2026-06-04 13:45 New test added | 4.9 | 10.0 | $0.038 | Compare | |
| 2026-05-22 00:18 Suite changed | 4.9 | 10.0 | $0.035 | Current run | |
| 2026-04-11 01:44 First recorded run | 5.1 | N/A | $0.032 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-05-22 00:18 · Suite changed | 60/60 attempts | 4.9 | 8.8 | 10.0 | 5/20 | 3 | 2,496 | 0 | $0.035 | 1.16s |
| 2026-07-16 22:33 · New test added | 66/66 attempts | 5.9 | 8.9 | 10.0 | 6/22 | 3 | 7,880 | 79,067 | $0.095 | 1.53s |
| Difference | — | -0.9 | -0.1 | 0.0 | -1 | 0 | -5384 | -79067 | -$0.060 | -375ms |
Benchmark coverage differs: 60/60 attempts (Target: 3 repeats per test) versus 66/66 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 MininonevsGLM 5.3 FlashlowGPT-5.4 MininonevsSeed 2.1 TurbononeGPT-5.4 MininonevsDots 3 Note PreviewmediumFree AvailableGPT-5.4 MininonevsGPT-5.4noneGPT-5.4 MininonevsStep 3.5 FlashmediumGPT-5.4 MininonevsSolar Pro 4noneGPT-5.4 MininonevsQwen3.5-35B-A3BnoneGPT-5.4 MininonevsNorth Mini CodemediumFree AvailableGPT-5.4 MininonevsQwen3.5-FlashnoneGPT-5.4 MininonevsNemotron 3 SupermediumFree Available
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 3.1 | 8.1 | |
| Coding | 6.8 | 10.0 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.5 | 4.4 | |
| General Intelligence | 4.8 | 10.0 | |
| Instructions following | 6.3 | 10.0 | |
| Puzzle Solving | 5.4 | 10.0 | |
| Tool Calling | 3.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |