Model comparison
GLM-4.5-Air vs Mistral Small
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 33.4 on the Noometry Index. Mistral Small costs 1.6× less per token, which makes it the better buy when GLM-4.5-Air's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. GLM-4.5-Air scores higher in 7 categories and Mistral Small in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5-Air leads 36.2 to 16.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 43% for GLM-4.5-Air and 37.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.20 / $1.10 for GLM-4.5-Air.
- Mistral Small accepts more context: 262K tokens versus 131K.
Side by side
| GLM-4.5-Air | Mistral Small | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 38.9 | 33.4 |
| Released | 2025-07-20 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 98K | 256K |
| Input $ / M tokens | $0.20 | $0.15 |
| Output $ / M tokens | $1.10 | $0.60 |
| Results tracked | 27 | 39 |
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 Small: 34.0 (#247)
| Benchmark | GLM-4.5-Air | Mistral Small |
|---|---|---|
| LMArena Coding | 1397 | 1362 |
| SciCode | — | 26.5% |
| GSO | 2.9% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, Mistral Small: 28.1 (#93)
| Benchmark | GLM-4.5-Air | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 24.1 (#166), Mistral Small: 19.8 (#250)
| Benchmark | GLM-4.5-Air | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 43% | 37.8% |
| LMArena Hard Prompts | 1379 | 1335 |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| ForecastBench | 59.2 | — |
| LiveBench | — | 44% |
Math GLM-4.5-Air leads
GLM-4.5-Air: 36.2 (#170), Mistral Small: 16.4 (#293)
| Benchmark | GLM-4.5-Air | Mistral Small |
|---|---|---|
| LMArena Math | 1396 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| Omni-MATH | 39.1% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 35.0 (#191), Mistral Small: 31.0 (#222)
| Benchmark | GLM-4.5-Air | Mistral Small |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 5.1% |
| LMArena Expert | 1370 | 1291 |
| GPQA Diamond | — | 47.5% |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| GPQA (HELM) | 59.4% | — |
| MMLU | — | 68.7% |
Multimodal Not comparable
GLM-4.5-Air: —, Mistral Small: 33.5 (#96)
| Benchmark | GLM-4.5-Air | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.1 (#135), Mistral Small: 45.5 (#169)
| Benchmark | GLM-4.5-Air | Mistral Small |
|---|---|---|
| LMArena Non-English | 1366 | 1315 |
| LMArena Chinese | 1426 | 1340 |
| LMArena French | 1399 | 1337 |
| LMArena German | 1377 | 1340 |
| LMArena Japanese | 1348 | 1275 |
| LMArena Korean | 1308 | 1259 |
| LMArena Russian | 1373 | 1324 |
| LMArena Spanish | 1386 | 1346 |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.6 (#171), Mistral Small: 66.4 (#209)
| Benchmark | GLM-4.5-Air | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1354 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Mistral Small: 40.4 (#156)
| Benchmark | GLM-4.5-Air | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1366 | 1327 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Mistral Small: 52.5 (#171)
| Benchmark | GLM-4.5-Air | Mistral Small |
|---|---|---|
| LMArena Text | 1384 | 1338 |
| LMArena Creative Writing | 1343 | 1305 |
| LMArena Multi-Turn | 1371 | 1344 |
| WildBench | 78.9% | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is GLM-4.5-Air better than Mistral Small?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 33.4 on the Noometry Index. Mistral Small costs 1.6× less per token, which makes it the better buy when GLM-4.5-Air's lead doesn't matter for your workload.
Which is cheaper, GLM-4.5-Air or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GLM-4.5-Air lists at $0.20 and $1.10.
Is GLM-4.5-Air or Mistral Small better for coding?
They score almost the same on coding (33.3 vs 34.0); test both on your own repository before choosing.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 131K.
How many benchmarks do GLM-4.5-Air and Mistral Small share?
19 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Mistral Small has 39.