#33
GPT-5 Mini
OpenAI ยท Release: 2025-08-07 ยท openai/gpt-5-mini::medium
Avg Score
5.77
Cost per result
1.200
Consistency
8.80
Total Cost
$0.084
Tests Correct
7
A test is fully passed only if every run passed for that test.
Wrong Tests
7
Attempt pass rate: 57.1%
Flaky tests
2
Response time: avg 21.47s ยท total 300.64s ยท max 82.55s
Did not follow instructions: 3
Wrong answer: 3
Timed out: 1
Top Models by Score
Choose the first model, then click a second model to open a side-by-side page.
Quick Compare
GPT-5 MinimediumvsQwen3.5-FlashmediumGPT-5 Minimediumvsgpt-oss-120bmediumFree AvailableGPT-5 MinimediumvsGPT-5 NanomediumGPT-5 MinimediumvsMiniMax M2.5mediumGPT-5 MinimediumvsQwen3.5-35B-A3BmediumGPT-5 MinimediumvsGemini 2.5 FlashnoneGPT-5 MinimediumvsGemini 3 Flash PreviewmediumGPT-5 MinimediumvsGemini 3.1 Pro PreviewmediumGPT-5 MinimediumvsStep 3.5 FlashmediumFree Available
Category Breakdown
| Category | Avg Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 7.00 | 9.62 | 2/3 |
| Data parsing and extraction | 9.88 | 10.00 | 2/2 |
| Domain specific | 1.00 | 7.21 | 0/3 |
| Instructions following | 7.00 | 6.64 | 1/2 |
| Puzzle Solving | 4.34 | 9.78 | 1/3 |
| Tool Calling | 10.00 | 10.00 | 1/1 |