Compare / grok-4-1-fast-non-reasoning vs GLM 4.6
grok-4-1-fast-non-reasoning vs GLM 4.6
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 | grok-4-1-fast-non-reasoning | GLM 4.6 |
|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 74.1% | 85.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 26.2% | 55.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 46.8% | 68.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 58.3% | 72.4% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 81.2% | 75.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 88.1% | 87.6% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 77.9% | 80.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 75.0% | 77.5% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 10.0% | 13.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.32 | 0.38 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 41.9 | 53.3 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 98.5% | 94.5% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 17.8% | 9.5% |
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.