Compare / Ministral 3 14B 2512 vs GLM 4.6
Ministral 3 14B 2512 vs GLM 4.6
15 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Ministral 3 14B 2512 | GLM 4.6 |
|---|---|---|---|
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 14.4 | 45.8 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 6.00 | 18.5 |
| Artificial Analysisreported | GPQA Diamond% of questions | 57.2% | 78.0% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 4.6% | 14.5% |
| Artificial Analysisreported | IFBench% of instructions | 32.0% | 43.4% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 26.3% | 54.0% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 9.7% | 49.4% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 4.5% | 28.8% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 6.6% | 13.4% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 27.2% | 76.9% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 24.0% | 13.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.32 | 0.38 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 31.4 | 53.3 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.6% | 94.5% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 19.4% | 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.