#17 GPT-5.4
medium- Cost
- $0.214
- Time
- 199.6s
- Tokens
- 14,349 tok
OpenAI
Release: 2026-03-05
Tested on: 2026-07-16 22:34
openai/gpt-5.4::medium
~1.5T total (~100B active)MoEClosedEstimated
(medium)
(none)
Summary
GPT-5.4 scores 8.5 on AI BENCHY and ranks #17. It has 10.0 reliability, a 77.3% pass rate, $1.533 total cost, and 23.10s average response time.
Model facts
Researched on 2026-08-12
- Parameters
- ~1.5T total (~100B 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.
8.5
Consistency
8.6
10.0
$1.533
Total Output Tokens
88,670
Total Input Tokens
81,127
Input Price
$2.500 / 1M
Output Price
$15.000 / 1M
Flaky tests
4
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 | 8.5 | 10.0 | $1.560 | Compare | |
| 2026-07-16 22:34 New test added | 8.5 | 10.0 | $1.533 | Current run | |
| 2026-06-04 13:46 New test added | 8.0 | 10.0 | $1.210 | Compare | |
| 2026-05-22 00:19 Suite changed | 7.9 | 10.0 | $1.140 | Compare | |
| 2026-04-11 01:44 First recorded run | 8.2 | N/A | $0.832 | 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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-07-16 22:34 · New test added | 66/66 attempts | 8.5 | 8.6 | 10.0 | 15/22 | 4 | 88,670 | 81,127 | $1.533 | 23.10s |
| 2026-05-22 00:19 · Suite changed | 60/60 attempts | 7.9 | 8.5 | 10.0 | 13/20 | 4 | 70,725 | 0 | $1.140 | 22.31s |
| Difference | — | +0.6 | +0.1 | 0.0 | +2 | 0 | +17945 | +81127 | +$0.394 | +795ms |
Benchmark coverage differs: 66/66 attempts (Target: 3 repeats per test) versus 60/60 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.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price |
|---|---|---|
| 2026-06-04 15:40 | $2.500 / 1M | $15.000 / 1M |
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-5.4mediumvsQwen3.8 MaxlowGPT-5.4mediumvsGrok 4.5mediumGPT-5.4mediumvsQwen3.6 Max PreviewmediumGPT-5.4mediumvsMuse Spark 1.2lowGPT-5.4mediumvsClaude Fable 5mediumGPT-5.4mediumvsGrok 4.6mediumGPT-5.4mediumvsMuse Spark 1.1mediumGPT-5.4mediumvsGrok 4.5lowGPT-5.4mediumvsMuse Spark 1.2mediumGPT-5.4mediumvsGPT-5.2medium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 8.3 | 10.0 | |
| Coding | 8.8 | 7.8 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 7.2 | |
| General Intelligence | 4.7 | 3.1 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 8.2 | 7.2 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |