Model card
Qwen/Qwen3-8B non-thinking (API).
Qwenapi8B params
§ 02 · Benchmarks
Every benchmark Qwen/Qwen3-8B non-thinking (API) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | CPTU-Bench | Natural Language Processing · Polish Text Understanding | tricky-questions | 2.8% | #45 | — | source ↗ |
| 02 | CPTU-Bench | Natural Language Processing · Polish Text Understanding | average | 3.1% | #58 | — | source ↗ |
| 03 | CPTU-Bench | Natural Language Processing · Polish Text Understanding | sentiment | 3.5% | #61 | — | source ↗ |
| 04 | CPTU-Bench | Natural Language Processing · Polish Text Understanding | language-understanding | 3.2% | #62 | — | source ↗ |
| 05 | CPTU-Bench | Natural Language Processing · Polish Text Understanding | phraseology | 2.8% | #69 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where Qwen/Qwen3-8B non-thinking (API) actually performs.
§ 06 · Sources & freshness
Where these numbers come from.
SpeakLeash/CPTU-Bench
5
results
5 of 5 rows marked verified.