Model comparison
GLM-4.5-Air vs Mistral
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 29.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. GLM-4.5-Air scores higher in 7 categories and Mistral in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5-Air leads 55.9 to 37.0.
- The biggest single-benchmark swing is MMLU-Pro: 76.2% for GLM-4.5-Air and 27.7% for Mistral.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5-Air | Mistral | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 38.9 | 29.9 |
| Released | 2025-07-20 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.5-Air: 33.3 (#259), Mistral: 33.8 (#250)
| Benchmark | GLM-4.5-Air | Mistral |
|---|---|---|
| LMArena Coding | 1397 | 1162 |
| GSO | 2.9% | — |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 24.1 (#166), Mistral: 22.2 (#200)
| Benchmark | GLM-4.5-Air | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1149 |
| Kagi LLM Benchmark | 43% | — |
| ForecastBench | 59.2 | — |
Math GLM-4.5-Air leads
GLM-4.5-Air: 36.2 (#170), Mistral: 22.3 (#278)
| Benchmark | GLM-4.5-Air | Mistral |
|---|---|---|
| Omni-MATH | 39.1% | 7.2% |
| LMArena Math | 1396 | 1180 |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 35.0 (#191), Mistral: 16.6 (#288)
| Benchmark | GLM-4.5-Air | Mistral |
|---|---|---|
| MMLU-Pro | 76.2% | 27.7% |
| GPQA (HELM) | 59.4% | 30.3% |
| LMArena Expert | 1370 | 1125 |
| Humanity's Last Exam | 8.1% | — |
| Vectara Hallucination Rate | 9.3% | — |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.1 (#135), Mistral: 32.8 (#254)
| Benchmark | GLM-4.5-Air | Mistral |
|---|---|---|
| LMArena Non-English | 1366 | 1129 |
| LMArena Chinese | 1426 | 1109 |
| LMArena French | 1399 | 1180 |
| LMArena German | 1377 | 1155 |
| LMArena Japanese | 1348 | 1013 |
| LMArena Korean | 1308 | 1032 |
| LMArena Russian | 1373 | 1168 |
| LMArena Spanish | 1386 | 1143 |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.6 (#171), Mistral: 52.6 (#288)
| Benchmark | GLM-4.5-Air | Mistral |
|---|---|---|
| IFEval | 81.2% | 56.8% |
| LMArena Instruction Following | 1354 | 1152 |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Mistral: 35.0 (#245)
| Benchmark | GLM-4.5-Air | Mistral |
|---|---|---|
| LMArena Longer Query | 1366 | 1153 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Mistral: 37.0 (#260)
| Benchmark | GLM-4.5-Air | Mistral |
|---|---|---|
| LMArena Text | 1384 | 1165 |
| LMArena Creative Writing | 1343 | 1158 |
| WildBench | 78.9% | 66% |
| LMArena Multi-Turn | 1371 | 1147 |
Frequently asked questions
Is GLM-4.5-Air better than Mistral?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 29.9 on the Noometry Index.
Is GLM-4.5-Air or Mistral better for coding?
They score almost the same on coding (33.3 vs 33.8); test both on your own repository before choosing.
How many benchmarks do GLM-4.5-Air and Mistral share?
22 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Mistral has 22.