Compare / Grok 4.6 vs GLM 4.7
Grok 4.6 vs GLM 4.7
19 results from 5 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Grok 4.6 | GLM 4.7 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,449 | 1,444 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,447 | 1,442 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,445 | 1,404 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,490 | 1,449 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,451 | 1,425 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,453 | 1,441 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,446 | 1,416 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 76.8 | 45.3 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 44.3 | 22.2 |
| Artificial Analysisreported | GPQA Diamond% of questions | 94.9% | 85.9% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 44.1% | 27.4% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 81.0% | 71.0% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 88.4% | 45.3% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 50.7% | 12.2% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 49.3% | 32.2% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 25.0% | 28.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.36 | 0.38 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 63.3 | 47.4 |
| Vending-Bench 2reported | Money after a yearUS dollars | $9,047.03 | $2,376.82 |
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.