#73 GPT-5 Mini
medium- Cost
- $0.007
- Time
- 42.9s
- Tokens
- 3,432 tok
OpenAI
Release: 2025-08-07
Tested on: 2026-05-22 00:16
openai/gpt-5-mini::medium
~400B total (~17B active)MoEClosedEstimated Summary
GPT-5 Mini scores 6.9 on AI BENCHY and ranks #73. It has 10.0 reliability, a 60.0% pass rate, $0.150 total cost, and 23.99s average response time.
What makes GPT-5 Mini unique: It stands out most in Coding, where it ranks #1, while General Intelligence is its weakest area at #17.
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. External research estimate; OpenAI does not disclose the architecture.
6.9
Consistency
8.7
10.0
$0.150
Total Output Tokens
70,358
Total Input Tokens
0
Input Price
$0.250 / 1M
Output Price
$2.000 / 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 02:07 Re-test | 8.1 | 10.0 | $0.241 | Compare | |
| 2026-07-16 22:27 New test added | 8.1 | 10.0 | $0.237 | Compare | |
| 2026-06-04 13:43 New test added | 7.3 | 10.0 | $0.159 | Compare | |
| 2026-05-22 00:16 Re-test | 6.9 | 10.0 | $0.150 | Current run | |
| 2026-04-11 01:44 First recorded run | 7.0 | N/A | $0.128 | Compare |
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 00:16 · Re-test | 60/60 attempts | 6.9 | 8.7 | 10.0 | 10/20 | 3 | 70,358 | 0 | $0.150 | 23.99s |
| 2026-07-16 22:27 · New test added | 66/66 attempts | 8.1 | 8.8 | 10.0 | 12/22 | 3 | 105,932 | 98,374 | $0.237 | 27.63s |
| Difference | — | -1.2 | -0.1 | 0.0 | -2 | 0 | -35574 | -98374 | -$0.088 | -3640ms |
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 MinimediumvsQwen3.8 2.4T A95BlowGPT-5 MinimediumvsMuse Glimmer 30BxhighGPT-5 MinimediumvsClaude Sonnet 5mediumGPT-5 MinimediumvsInklinghighGPT-5 MinimediumvsGemini 2.5 FlashmediumGPT-5 MinimediumvsMuse Spark 1.1highGPT-5 MinimediumvsClaude Fable 5.1mediumGPT-5 MinimediumvsDeepSeek V4 Flash 0731lowGPT-5 MinimediumvsMuse Spark 1.1lowGPT-5 MinimediumvsDeepSeek V4 Flash 0731high
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 7.1 | 7.6 | |
| Coding | 10.0 | 10.0 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.6 | 7.2 | |
| General Intelligence | 4.5 | 10.0 | |
| Instructions following | 7.9 | 6.5 | |
| Puzzle Solving | 5.6 | 9.8 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |