GLM 5.3 Flash — Benchmarks
Benchmark scores for GLM 5.3 Flash aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #22 of 123 open modelscomposite 62.6/100 across 8 benchmarks in 3 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SciCode | 46.1% | #14 / 50 | #80 / 155 |
| LiveBench Coding | 79.0 | #4 / 16 | #19 / 54 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 93.9% | #7 / 74 | #42 / 270 |
| LiveBench Math | 81.2 | #12 / 16 | #46 / 54 |
| ProofBench | 21.0% | #8 / 21 | #35 / 64 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 90.1% | #9 / 83 | #36 / 291 |
| LiveBench Reasoning | 77.6 | #12 / 16 | #44 / 54 |
| CritPt | 15.4% | #6 / 50 | #51 / 167 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.