Compare / Qwen3 8B vs Claude Opus 4.5
Qwen3 8B vs Claude Opus 4.5
13 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Qwen3 8B | Claude Opus 4.5 |
|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 82.3% | 90.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 14.6% | 73.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 41.8% | 68.4% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 42.6% | 77.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 93.8% | 68.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 88.6% | 89.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 80.5% | 79.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 13.5% | 84.5% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 17.0% | 3.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.36 | 0.39 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 28.0 | 70.4 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.9% | 98.7% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 4.8% | 10.9% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.