Model comparison
GLM-4.5 vs Mistral Medium
GLM-4.5 is the stronger model overall, scoring 42.0 to 36.3 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. GLM-4.5 scores higher in 6 categories and Mistral Medium in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5 leads 39.0 to 28.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.9% for GLM-4.5 and 50% for Mistral Medium.
- GLM-4.5 is cheaper at $0.60 / $2.20 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 | Mistral Medium | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 42.0 | 36.3 |
| Released | 2025-07-27 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 98K | 262K |
| Input $ / M tokens | $0.60 | $1.50 |
| Output $ / M tokens | $2.20 | $7.50 |
| Results tracked | 27 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5 leads
GLM-4.5: 41.4 (#125), Mistral Medium: 34.2 (#243)
| Benchmark | GLM-4.5 | Mistral Medium |
|---|---|---|
| WeirdML | 40.6% | 43.7% |
| LMArena Coding | 1434 | 1434 |
| ALE-Bench | 344.82 | 763.98 |
| FrontierCode | — | 8% |
| SWE-bench Verified (bash only) | 54.2% | — |
| SciCode | — | 40.2% |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
GLM-4.5: —, Mistral Medium: 28.3 (#90)
| Benchmark | GLM-4.5 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning GLM-4.5 leads
GLM-4.5: 28.6 (#100), Mistral Medium: 24.0 (#167)
| Benchmark | GLM-4.5 | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 50% |
| LMArena Hard Prompts | 1429 | 1426 |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math GLM-4.5 leads
GLM-4.5: 39.0 (#116), Mistral Medium: 28.1 (#245)
| Benchmark | GLM-4.5 | Mistral Medium |
|---|---|---|
| LMArena Math | 1427 | 1408 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GLM-4.5 leads
GLM-4.5: 35.9 (#179), Mistral Medium: 25.0 (#265)
| Benchmark | GLM-4.5 | Mistral Medium |
|---|---|---|
| Humanity's Last Exam | 8.3% | 4.5% |
| LMArena Expert | 1433 | 1408 |
| GPQA Diamond | — | 59.5% |
| Confabulations | 11.3% | — |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Not comparable
GLM-4.5: —, Mistral Medium: 35.3 (#88)
| Benchmark | GLM-4.5 | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Too close to call
GLM-4.5: 52.8 (#77), Mistral Medium: 52.1 (#91)
| Benchmark | GLM-4.5 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1417 | 1408 |
| LMArena Chinese | 1465 | 1447 |
| LMArena French | 1418 | 1459 |
| LMArena German | 1407 | 1432 |
| LMArena Japanese | 1415 | 1378 |
| LMArena Korean | 1380 | 1380 |
| LMArena Russian | 1414 | 1411 |
| LMArena Spanish | 1454 | 1433 |
Instruction Following Too close to call
GLM-4.5: 74.1 (#104), Mistral Medium: 73.7 (#116)
| Benchmark | GLM-4.5 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1404 | 1398 |
Long Context Mistral Medium leads
GLM-4.5: 38.2 (#201), Mistral Medium: 42.9 (#114)
| Benchmark | GLM-4.5 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1412 | 1406 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Mistral Medium leads
GLM-4.5: 57.5 (#127), Mistral Medium: 60.0 (#103)
| Benchmark | GLM-4.5 | Mistral Medium |
|---|---|---|
| LMArena Text | 1430 | 1424 |
| LMArena Creative Writing | 1395 | 1391 |
| Short-Story Creative Writing | 73.4% | 77.3% |
| LMArena Multi-Turn | 1415 | 1418 |
| EQ-Bench Creative Writing | 1343 | — |
Frequently asked questions
Is GLM-4.5 better than Mistral Medium?
GLM-4.5 is the stronger model overall, scoring 42.0 to 36.3 on the Noometry Index.
Which is cheaper, GLM-4.5 or Mistral Medium?
GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is GLM-4.5 or Mistral Medium better for coding?
GLM-4.5 scores higher on coding benchmarks: 41.4 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 131K.
How many benchmarks do GLM-4.5 and Mistral Medium share?
22 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Mistral Medium has 36.