Compare / GPT-4.1 vs grok-4-1-fast-non-reasoning
GPT-4.1 vs grok-4-1-fast-non-reasoning
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 | GPT-4.1 | grok-4-1-fast-non-reasoning |
|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 86.5% | 74.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 23.9% | 26.2% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 38.9% | 46.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 54.0% | 58.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 100.0% | 81.2% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 88.7% | 88.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 78.9% | 77.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 68.0% | 75.0% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 6.0% | 10.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.33 | 0.32 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 67.5 | 41.9 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.9% | 98.5% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 5.6% | 17.8% |
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.