Model comparison
GLM-4.5-Air vs Mistral Large
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 31.6 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AISummary
- They share 24 benchmarks with published results for both. GLM-4.5-Air scores higher in 8 categories and Mistral Large in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5-Air leads 33.8 to 17.1.
- The biggest single-benchmark swing is MMLU-Pro: 76.2% for GLM-4.5-Air and 59.9% for Mistral Large.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $2 / $6 for Mistral Large.
Side by side
| GLM-4.5-Air | Mistral Large | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 38.7 | 31.6 |
| Released | 2025-07-20 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 98K | 16K |
| Input $ / M tokens | $0.20 | $2 |
| Output $ / M tokens | $1.10 | $6 |
| Results tracked | 27 | 51 |
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 Large: 33.8 (#240)
| Benchmark | GLM-4.5-Air | Mistral Large |
|---|---|---|
| LMArena Coding | 1397 | 1277 |
| SciCode | — | 36.2% |
| GSO | 2.9% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, Mistral Large: 28.4 (#83)
| Benchmark | GLM-4.5-Air | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 23.3 (#166), Mistral Large: 15.4 (#305)
| Benchmark | GLM-4.5-Air | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1257 |
| ForecastBench | 59.2 | 57.1 |
| SimpleBench | — | 22.5% |
| Kagi LLM Benchmark | 43% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Epoch Capabilities Index | — | 128.52 |
| LiveBench | — | 48.4% |
Math GLM-4.5-Air leads
GLM-4.5-Air: 33.8 (#166), Mistral Large: 17.1 (#285)
| Benchmark | GLM-4.5-Air | Mistral Large |
|---|---|---|
| Omni-MATH | 39.1% | 28.1% |
| LMArena Math | 1396 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 34.6 (#184), Mistral Large: 30.0 (#224)
| Benchmark | GLM-4.5-Air | Mistral Large |
|---|---|---|
| MMLU-Pro | 76.2% | 59.9% |
| Vectara Hallucination Rate | 9.3% | 4.5% |
| GPQA (HELM) | 59.4% | 43.5% |
| LMArena Expert | 1370 | 1232 |
| GPQA Diamond | — | 51.3% |
| Humanity's Last Exam | 8.1% | — |
| Confabulations | — | 21.4% |
| MMLU | — | 80% |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.4 (#130), Mistral Large: 40.1 (#214)
| Benchmark | GLM-4.5-Air | Mistral Large |
|---|---|---|
| LMArena Non-English | 1366 | 1237 |
| LMArena Chinese | 1427 | 1240 |
| LMArena French | 1399 | 1324 |
| LMArena German | 1376 | 1254 |
| LMArena Japanese | 1348 | 1187 |
| LMArena Korean | 1306 | 1202 |
| LMArena Russian | 1373 | 1257 |
| LMArena Spanish | 1385 | 1268 |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.8 (#165), Mistral Large: 68.1 (#186)
| Benchmark | GLM-4.5-Air | Mistral Large |
|---|---|---|
| IFEval | 81.2% | 87.7% |
| LMArena Instruction Following | 1353 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#130), Mistral Large: 38.3 (#194)
| Benchmark | GLM-4.5-Air | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1367 | 1262 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 56.1 (#134), Mistral Large: 40.9 (#237)
| Benchmark | GLM-4.5-Air | Mistral Large |
|---|---|---|
| LMArena Text | 1384 | 1266 |
| LMArena Creative Writing | 1343 | 1243 |
| WildBench | 78.9% | 80.1% |
| LMArena Multi-Turn | 1371 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is GLM-4.5-Air better than Mistral Large?
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 31.6 on the Noometry Index.
Which is cheaper, GLM-4.5-Air or Mistral Large?
GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Mistral Large lists at $2 and $6.
Is GLM-4.5-Air or Mistral Large 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?
Both accept 131K tokens.
How many benchmarks do GLM-4.5-Air and Mistral Large share?
24 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Mistral Large has 51.