PIQA leaderboard
- GPT-4o-mini leads
- 88.7%
- models measured
- 3
- lead over #2
- +6.1 pts
- median
- 82.6%
Leader on PIQA · read October 22
On October 22, 2026, 4 of our catalog's models had a PIQA result, and OpenAI GPT-4o-mini led with 88.7%, ahead of Google Gemini 1.5 Flash at 87.5%.
Physical common sense: which of two ways reaches an everyday goal. Share correct.
Role in the index
PIQA is shown as published and does not feed any of our indexes. Read the methodology
| # | Model | Result | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | GPT-4o-miniOpenAI | 88.7% | Not benchmarked | $0.60 | |
| 2 | Gemini 1.5 FlashRetiredGoogle | 87.5% | Not benchmarked | $0.30 | |
| 3 | Qwen2.5 72B InstructQwen | 82.6% | Not benchmarked | $0.40 | |
| 4 | Llama 3.1 8B InstructMeta Llama | 81.2% | Not benchmarked | $0.08 |
Only models in our catalog are listed, and each appears once with its best published run. 215 rows were read from the source on October 22, 2026, and rows that match no catalog model are left out.