Model comparison
GLM-4.5-Air vs Mistral Medium
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 36.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. GLM-4.5-Air scores higher in 3 categories and Mistral Medium in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.5-Air leads 34.6 to 24.9.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 9.3% for GLM-4.5-Air and 22.7% for Mistral Medium.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 131K.
Side by side
| GLM-4.5-Air | Mistral Medium | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 38.7 | 36.0 |
| Released | 2025-07-20 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 98K | 262K |
| Input $ / M tokens | $0.20 | $1.50 |
| Output $ / M tokens | $1.10 | $7.50 |
| Results tracked | 27 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.5-Air: 34.5 (#225), Mistral Medium: 33.8 (#241)
| Benchmark | GLM-4.5-Air | Mistral Medium |
|---|---|---|
| LMArena Coding | 1397 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| GSO | 2.9% | — |
| WeirdML | — | 43.7% |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, Mistral Medium: 28.1 (#84)
| Benchmark | GLM-4.5-Air | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Too close to call
GLM-4.5-Air: 23.3 (#166), Mistral Medium: 23.3 (#165)
| Benchmark | GLM-4.5-Air | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 43% | 50% |
| LMArena Hard Prompts | 1379 | 1426 |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| ForecastBench | 59.2 | — |
Math GLM-4.5-Air leads
GLM-4.5-Air: 33.8 (#166), Mistral Medium: 27.2 (#238)
| Benchmark | GLM-4.5-Air | Mistral Medium |
|---|---|---|
| LMArena Math | 1396 | 1409 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| Omni-MATH | 39.1% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 34.6 (#184), Mistral Medium: 24.9 (#260)
| Benchmark | GLM-4.5-Air | Mistral Medium |
|---|---|---|
| Humanity's Last Exam | 8.1% | 4.5% |
| Vectara Hallucination Rate | 9.3% | 22.7% |
| LMArena Expert | 1370 | 1408 |
| GPQA Diamond | — | 59.5% |
| MMLU-Pro | 76.2% | — |
| GPQA (HELM) | 59.4% | — |
Multimodal Not comparable
GLM-4.5-Air: —, Mistral Medium: 34.6 (#82)
| Benchmark | GLM-4.5-Air | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
GLM-4.5-Air: 49.4 (#130), Mistral Medium: 52.3 (#86)
| Benchmark | GLM-4.5-Air | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1366 | 1408 |
| LMArena Chinese | 1427 | 1448 |
| LMArena French | 1399 | 1460 |
| LMArena German | 1376 | 1433 |
| LMArena Japanese | 1348 | 1378 |
| LMArena Korean | 1306 | 1382 |
| LMArena Russian | 1373 | 1411 |
| LMArena Spanish | 1385 | 1433 |
Instruction Following Mistral Medium leads
GLM-4.5-Air: 69.8 (#165), Mistral Medium: 73.9 (#111)
| Benchmark | GLM-4.5-Air | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1353 | 1398 |
| IFEval | 81.2% | — |
Long Context Mistral Medium leads
GLM-4.5-Air: 41.6 (#130), Mistral Medium: 42.9 (#108)
| Benchmark | GLM-4.5-Air | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1367 | 1406 |
Writing & Preference Mistral Medium leads
GLM-4.5-Air: 56.1 (#134), Mistral Medium: 60.2 (#97)
| Benchmark | GLM-4.5-Air | Mistral Medium |
|---|---|---|
| LMArena Text | 1384 | 1424 |
| LMArena Creative Writing | 1343 | 1391 |
| LMArena Multi-Turn | 1371 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Mistral Medium?
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 36.0 on the Noometry Index.
Which is cheaper, GLM-4.5-Air or Mistral Medium?
GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is GLM-4.5-Air or Mistral Medium better for coding?
They score almost the same on coding (34.5 vs 33.8); test both on your own repository before choosing.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 131K.
How many benchmarks do GLM-4.5-Air and Mistral Medium share?
20 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Mistral Medium has 36.