#94 GPT-5 Nano
medium- Cost
- $0.006
- Time
- 108.5s
- Tokens
- 13,209 tok
OpenAI
Release: 2025-08-07
Tested on: 2026-05-22 00:17
openai/gpt-5-nano::medium
~120B total (~5B active)MoEClosedEstimated Summary
GPT-5 Nano scores 6.1 on AI BENCHY and ranks #94. It has 10.0 reliability, a 55.0% pass rate, $0.076 total cost, and 43.11s average response time.
What makes GPT-5 Nano unique: It stands out most in Combined, where it ranks #1, while Data parsing and extraction 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.
6.1
Consistency
7.1
10.0
$0.076
Total Output Tokens
184,922
Total Input Tokens
0
Input Price
$0.050 / 1M
Output Price
$0.400 / 1M
Flaky tests
7
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 02:07 Re-test | 6.0 | 10.0 | $0.118 | Compare | |
| 2026-07-16 22:32 New test added | 6.1 | 10.0 | $0.114 | Compare | |
| 2026-06-04 13:44 New test added | 6.3 | 10.0 | $0.081 | Compare | |
| 2026-05-22 00:17 Suite changed | 6.1 | 10.0 | $0.076 | Current run | |
| 2026-04-11 01:44 First recorded run | 6.3 | N/A | $0.066 | 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 00:17 · Suite changed | 60/60 attempts | 6.1 | 7.1 | 10.0 | 8/20 | 7 | 184,922 | 0 | $0.076 | 43.11s |
| 2026-08-14 02:07 · Re-test | 66/66 attempts | 6.0 | 6.6 | 10.0 | 8/22 | 9 | 282,437 | 94,944 | $0.118 | 54.20s |
| Difference | — | +0.1 | +0.5 | 0.0 | 0 | -2 | -97515 | -94944 | -$0.043 | -11090ms |
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 NanomediumvsGPT-5.6 TerranoneGPT-5 NanomediumvsQwen3.5-FlashnoneGPT-5 NanomediumvsGemini 2.5 FlashnoneGPT-5 NanomediumvsQwen3.5-35B-A3BnoneGPT-5 NanomediumvsTrinity Large ThinkinglowGPT-5 NanomediumvsStep 3.5 FlashmediumGPT-5 NanomediumvsNemotron 3 UltranoneFree AvailableGPT-5 NanomediumvsDots 3 Note PreviewmediumFree AvailableGPT-5 NanomediumvsQwen3.5 Plus 2026-04-20noneGPT-5 NanomediumvsGPT-5.4 Mininone
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 6.5 | 7.9 | |
| Coding | 5.4 | 6.6 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 3.7 | 1.7 | |
| Domain specific | 5.2 | 4.4 | |
| General Intelligence | 4.1 | 10.0 | |
| Instructions following | 9.8 | 10.0 | |
| Puzzle Solving | 5.3 | 7.2 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |