#58 GPT-5.5
none- Cost
- $0.090
- Time
- 54.3s
- Tokens
- 3,063 tok
OpenAI
Release: 2026-04-24
Tested on: 2026-04-24 19:59
openai/gpt-5.5::none
~1.5T total (~100B active)MoEClosedEstimated
Summary
GPT-5.5 scores 6.8 on AI BENCHY and ranks #58. It has N/A reliability, a 61.1% pass rate, $0.195 total cost, and 1.83s average response time.
What makes GPT-5.5 unique: It stands out most in General Intelligence, where it ranks #1, while Combined is its weakest area at #18. 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
- ~1.5T total (~100B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. External estimate; vendor does not disclose the architecture or count.
6.8
Consistency
8.3
N/A
$0.195
Total Output Tokens
1,910
Total Input Tokens
0
Input Price
$5.000 / 1M
Output Price
$30.000 / 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 02:17 Re-test | 7.0 | 10.0 | $0.544 | Compare | |
| 2026-07-16 22:34 New test added | 6.9 | 10.0 | $0.544 | Compare | |
| 2026-06-04 13:46 New test added | 6.4 | 10.0 | $0.231 | Compare | |
| 2026-05-22 00:19 Suite changed | 6.5 | 10.0 | $0.217 | Compare | |
| 2026-04-24 19:59 Initial run | 6.8 | N/A | $0.195 | 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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-04-24 19:59 · Initial run | 54/54 attempts | 6.8 | 8.3 | N/A | 9/18 | 4 | 1,910 | 0 | $0.195 | 1.83s |
| 2026-08-14 02:17 · Re-test | 66/66 attempts | 7.0 | 9.2 | 10.0 | 12/22 | 2 | 4,915 | 79,294 | $0.544 | 2.35s |
| Difference | — | -0.2 | -0.9 | -3 | +2 | -3005 | -79294 | -$0.350 | -528ms |
Benchmark coverage differs: 54/54 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
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 6.9 | 7.9 | |
| Coding | 10.0 | 10.0 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 2.9 | 7.2 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 6.2 | 5.8 | |
| Puzzle Solving | 6.7 | 7.9 | |
| Tool Calling | 10.0 | 10.0 |