Compare / Kimi K2 0711 vs grok-4-1-fast-non-reasoning
Kimi K2 0711 vs grok-4-1-fast-non-reasoning
18 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Kimi K2 0711 | grok-4-1-fast-non-reasoning |
|---|---|---|---|
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 12.7 | 11.3 |
| Artificial Analysisreported | GPQA Diamond% of questions | 76.6% | 63.7% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 7.4% | 5.1% |
| Artificial Analysisreported | IFBench% of instructions | 41.5% | 36.5% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 53.0% | 31.3% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 15.9% | 14.4% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 61.1% | 63.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 87.3% | 74.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 29.0% | 26.2% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 50.6% | 46.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 59.1% | 58.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 75.0% | 81.2% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 81.6% | 88.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 78.7% | 77.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 66.5% | 75.0% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 22.0% | 10.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.29 | 0.32 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 52.5 | 41.9 |
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.