Model comparison
GLM-5.3 vs Mistral Medium 3.5
GLM-5.3 is the stronger model overall, scoring 54.8 to 40.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. GLM-5.3 scores higher in 8 categories and Mistral Medium 3.5 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.3 leads 46.1 to 17.3.
- The biggest single-benchmark swing is NYT Connections (extended): 74.2% for GLM-5.3 and 12.9% for Mistral Medium 3.5.
- GLM-5.3 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- GLM-5.3 accepts more context: 1M tokens versus 262K.
Side by side
| GLM-5.3 | Mistral Medium 3.5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 54.8 | 40.2 |
| Released | 2026-08-14 | — |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 131K | 210K |
| Input $ / M tokens | $1.40 | $1.50 |
| Output $ / M tokens | $4.40 | $7.50 |
| Results tracked | 42 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3 leads
GLM-5.3: 59.5 (#14), Mistral Medium 3.5: 36.0 (#213)
| Benchmark | GLM-5.3 | Mistral Medium 3.5 |
|---|---|---|
| LMArena WebDev | 1622 | 1264 |
| LMArena Coding | 1496 | 1461 |
| DeepSWE | 69% | — |
| FrontierCode | 40.1% | — |
| CursorBench | 42.6% | — |
| FrontierSWE | 30.2% | — |
| SciCode | 59% | — |
| WeirdML | 75.4% | — |
| ALE-Bench | 1,317 | — |
Agentic & Tool Use Not comparable
GLM-5.3: 36.4 (#38), Mistral Medium 3.5: —
| Benchmark | GLM-5.3 | Mistral Medium 3.5 |
|---|---|---|
| APEX-Agents | 56.6% | — |
| Vending-Bench 2 | 8,164 | — |
Reasoning GLM-5.3 leads
GLM-5.3: 46.1 (#46), Mistral Medium 3.5: 17.3 (#295)
| Benchmark | GLM-5.3 | Mistral Medium 3.5 |
|---|---|---|
| NYT Connections (extended) | 74.2% | 12.9% |
| LMArena Hard Prompts | 1489 | 1436 |
| Epoch Capabilities Index | 155.61 | 141.35 |
| Kagi LLM Benchmark | — | 41.4% |
| CritPt | 19.1% | — |
| Chess Puzzles | 21% | — |
| Mystery Game Puzzles | 33% | — |
| DTBench | 87.7% | — |
| LMCA | 55.5% | — |
| Bench to the Future 3 | 0.15 | — |
Math GLM-5.3 leads
GLM-5.3: 62.3 (#33), Mistral Medium 3.5: 39.1 (#113)
| Benchmark | GLM-5.3 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1489 | 1431 |
| FrontierMath (Tiers 1-3) | 68.8% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 91.1% | — |
| ProofBench | 49% | — |
Knowledge GLM-5.3 leads
GLM-5.3: 58.3 (#37), Mistral Medium 3.5: 40.0 (#126)
| Benchmark | GLM-5.3 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1516 | 1432 |
| GPQA Diamond | 90.9% | — |
| SimpleQA Verified | 41% | — |
Multimodal Not comparable
GLM-5.3: —, Mistral Medium 3.5: 38.3 (#65)
| Benchmark | GLM-5.3 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1223 |
Multilingual GLM-5.3 leads
GLM-5.3: 55.7 (#28), Mistral Medium 3.5: 51.9 (#100)
| Benchmark | GLM-5.3 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1457 | 1404 |
| LMArena Chinese | 1528 | 1442 |
| LMArena French | 1499 | 1448 |
| LMArena German | 1499 | 1451 |
| LMArena Korean | 1472 | 1385 |
| LMArena Russian | 1463 | 1395 |
| LMArena Spanish | 1460 | 1409 |
| LMArena Japanese | 1453 | — |
Instruction Following GLM-5.3 leads
GLM-5.3: 77.5 (#23), Mistral Medium 3.5: 74.6 (#90)
| Benchmark | GLM-5.3 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1477 | 1415 |
Long Context GLM-5.3 leads
GLM-5.3: 45.4 (#41), Mistral Medium 3.5: 43.2 (#103)
| Benchmark | GLM-5.3 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1482 | 1415 |
Writing & Preference GLM-5.3 leads
GLM-5.3: 75.7 (#6), Mistral Medium 3.5: 58.5 (#117)
| Benchmark | GLM-5.3 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1471 | 1421 |
| LMArena Creative Writing | 1457 | 1374 |
| LMArena Multi-Turn | 1472 | 1423 |
| EQ-Bench Creative Writing | 2075 | — |
| EQ-Bench 4 | — | 993 |
Frequently asked questions
Is GLM-5.3 better than Mistral Medium 3.5?
GLM-5.3 is the stronger model overall, scoring 54.8 to 40.2 on the Noometry Index.
Which is cheaper, GLM-5.3 or Mistral Medium 3.5?
GLM-5.3 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.
Is GLM-5.3 or Mistral Medium 3.5 better for coding?
GLM-5.3 scores higher on coding benchmarks: 59.5 versus 36.0 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3 does, with 1M tokens against 262K.
How many benchmarks do GLM-5.3 and Mistral Medium 3.5 share?
19 benchmarks have published results for both models. GLM-5.3 has 42 scored results on Noometry and Mistral Medium 3.5 has 22.