Model comparison
GLM-5 vs Magistral Medium
GLM-5 is the stronger model overall, scoring 46.1 to 35.2 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. GLM-5 scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5 leads 66.0 to 46.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for GLM-5 and 16.2% for Magistral Medium.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 205K.
Side by side
| GLM-5 | Magistral Medium | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 46.1 | 35.2 |
| Released | 2026-02-11 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 16K |
| Input $ / M tokens | $1 | $2 |
| Output $ / M tokens | $3.20 | $5 |
| Results tracked | 45 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Magistral Medium: 39.1 (#161)
| Benchmark | GLM-5 | Magistral Medium |
|---|---|---|
| LMArena Coding | 1461 | 1319 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 39.2% |
| WeirdML | 48.2% | — |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), Magistral Medium: —
| Benchmark | GLM-5 | Magistral Medium |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#116), Magistral Medium: 8.6 (#348)
| Benchmark | GLM-5 | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 4.9% | 0% |
| Kagi LLM Benchmark | 75% | 16.2% |
| ARC-AGI-1 | 44.7% | 6.1% |
| LMArena Hard Prompts | 1452 | 1267 |
| SimpleBench | 53.2% | — |
| NYT Connections (extended) | 74.8% | — |
| CritPt | — | 0.3% |
| Chess Puzzles | 10% | — |
| Epoch Capabilities Index | 145.83 | — |
| ForecastBench | 61 | — |
Math GLM-5 leads
GLM-5: 46.4 (#71), Magistral Medium: 35.1 (#189)
| Benchmark | GLM-5 | Magistral Medium |
|---|---|---|
| LMArena Math | 1440 | 1250 |
| MathArena Final-Answer Competitions | 65.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), Magistral Medium: 33.5 (#202)
| Benchmark | GLM-5 | Magistral Medium |
|---|---|---|
| LMArena Expert | 1454 | 1223 |
| GPQA Diamond | 87.8% | — |
| Vectara Hallucination Rate | 10.1% | — |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), Magistral Medium: 39.6 (#224)
| Benchmark | GLM-5 | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1430 | 1232 |
| LMArena Chinese | 1511 | 1227 |
| LMArena French | 1455 | 1267 |
| LMArena German | 1445 | 1248 |
| LMArena Japanese | 1416 | 1175 |
| LMArena Korean | 1423 | 1125 |
| LMArena Russian | 1436 | 1224 |
| LMArena Spanish | 1454 | 1271 |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), Magistral Medium: 66.0 (#211)
| Benchmark | GLM-5 | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1428 | 1254 |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), Magistral Medium: 39.3 (#183)
| Benchmark | GLM-5 | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1446 | 1295 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Magistral Medium: 46.3 (#219)
| Benchmark | GLM-5 | Magistral Medium |
|---|---|---|
| LMArena Text | 1446 | 1255 |
| LMArena Creative Writing | 1439 | 1245 |
| LMArena Multi-Turn | 1456 | 1275 |
| EQ-Bench Creative Writing | 1601 | — |
Frequently asked questions
Is GLM-5 better than Magistral Medium?
GLM-5 is the stronger model overall, scoring 46.1 to 35.2 on the Noometry Index.
Which is cheaper, GLM-5 or Magistral Medium?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; Magistral Medium lists at $2 and $5.
Is GLM-5 or Magistral Medium better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 205K.
How many benchmarks do GLM-5 and Magistral Medium share?
20 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Magistral Medium has 22.