Model comparison
GLM-4.5 vs Ministral 3B
GLM-4.5 is the stronger model overall, scoring 41.4 to 25.6 on the Noometry Index. Ministral 3B costs 25× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in knowledge, where GLM-4.5 leads 35.5 to 10.4.
- Ministral 3B is cheaper at $0.04 / $0.04 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
- GLM-4.5 accepts more context: 131K tokens versus 128K.
Side by side
| GLM-4.5 | Ministral 3B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 41.4 | 25.6 |
| Released | 2025-07-27 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 131K | 128K |
| Max output | 98K | 128K |
| Input $ / M tokens | $0.60 | $0.04 |
| Output $ / M tokens | $2.20 | $0.04 |
| Results tracked | 27 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GLM-4.5: 41.1 (#121), Ministral 3B: —
| Benchmark | GLM-4.5 | Ministral 3B |
|---|---|---|
| SWE-bench Verified (bash only) | 54.2% | — |
| WeirdML | 40.6% | — |
| LMArena Coding | 1434 | — |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
Reasoning GLM-4.5 leads
GLM-4.5: 27.7 (#99), Ministral 3B: 17.7 (#278)
| Benchmark | GLM-4.5 | Ministral 3B |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | — |
| LMArena Hard Prompts | 1430 | — |
| DTBench | — | 51.7% |
| LMCA | — | 5.5% |
| Epoch Capabilities Index | — | 118.08 |
Math GLM-4.5 leads
GLM-4.5: 36.3 (#119), Ministral 3B: 24.5 (#257)
| Benchmark | GLM-4.5 | Ministral 3B |
|---|---|---|
| LMArena Math | 1427 | — |
| MATH Level 5 | — | 14.4% |
Knowledge GLM-4.5 leads
GLM-4.5: 35.5 (#172), Ministral 3B: 10.4 (#297)
| Benchmark | GLM-4.5 | Ministral 3B |
|---|---|---|
| GPQA Diamond | — | 25.3% |
| Humanity's Last Exam | 8.3% | — |
| Confabulations | 11.3% | — |
| Vectara Hallucination Rate | — | 7.3% |
| LMArena Expert | 1433 | — |
Multilingual Not comparable
GLM-4.5: 53.0 (#74), Ministral 3B: —
| Benchmark | GLM-4.5 | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1417 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1423 | — |
| LMArena German | 1406 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1382 | — |
| LMArena Russian | 1414 | — |
| LMArena Spanish | 1454 | — |
Instruction Following Not comparable
GLM-4.5: 74.3 (#100), Ministral 3B: —
| Benchmark | GLM-4.5 | Ministral 3B |
|---|---|---|
| LMArena Instruction Following | 1405 | — |
Long Context Not comparable
GLM-4.5: 38.2 (#196), Ministral 3B: —
| Benchmark | GLM-4.5 | Ministral 3B |
|---|---|---|
| Fiction.LiveBench | 58.3% | — |
| LMArena Longer Query | 1413 | — |
Writing & Preference Not comparable
GLM-4.5: 57.7 (#121), Ministral 3B: —
| Benchmark | GLM-4.5 | Ministral 3B |
|---|---|---|
| LMArena Text | 1430 | — |
| LMArena Creative Writing | 1395 | — |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |
| LMArena Multi-Turn | 1415 | — |
Frequently asked questions
Is GLM-4.5 better than Ministral 3B?
GLM-4.5 is the stronger model overall, scoring 41.4 to 25.6 on the Noometry Index. Ministral 3B costs 25× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.
Which is cheaper, GLM-4.5 or Ministral 3B?
Ministral 3B is cheaper. It lists at $0.04 per million input tokens and $0.04 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.
Which has the bigger context window?
GLM-4.5 does, with 131K tokens against 128K.
How many benchmarks do GLM-4.5 and Ministral 3B share?
0 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Ministral 3B has 6.