Model comparison
GLM-5.1 vs Ministral 8B
GLM-5.1 is the stronger model overall, scoring 47.8 to 28.2 on the Noometry Index. Ministral 8B costs 14× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Mistral AISummary
- They share 13 benchmarks with published results for both. GLM-5.1 scores higher in 9 categories and Ministral 8B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.1 leads 54.9 to 12.6.
- The biggest single-benchmark swing is GPQA Diamond: 89.9% for GLM-5.1 and 27.1% for Ministral 8B.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Ministral 8B accepts more context: 262K tokens versus 200K.
Side by side
| GLM-5.1 | Ministral 8B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 47.8 | 28.2 |
| Released | 2026-04-07 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 200K | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $1.40 | $0.15 |
| Output $ / M tokens | $4.40 | $0.15 |
| Results tracked | 41 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.7 (#55), Ministral 8B: 35.0 (#230)
| Benchmark | GLM-5.1 | Ministral 8B |
|---|---|---|
| LMArena Coding | 1485 | 1202 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use GLM-5.1 leads
GLM-5.1: 24.9 (#113), Ministral 8B: 16.4 (#148)
| Benchmark | GLM-5.1 | Ministral 8B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 11.1% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), Ministral 8B: 18.4 (#281)
| Benchmark | GLM-5.1 | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1472 | 1191 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 45.7% |
| Epoch Capabilities Index | 149.84 | — |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), Ministral 8B: 25.7 (#267)
| Benchmark | GLM-5.1 | Ministral 8B |
|---|---|---|
| LMArena Math | 1473 | 1188 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| MATH Level 5 | — | 14.9% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), Ministral 8B: 12.6 (#297)
| Benchmark | GLM-5.1 | Ministral 8B |
|---|---|---|
| GPQA Diamond | 89.9% | 27.1% |
| LMArena Expert | 1476 | 1170 |
| SimpleQA Verified | 34% | — |
| Vectara Hallucination Rate | — | 7.4% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Ministral 8B: 35.1 (#247)
| Benchmark | GLM-5.1 | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1447 | 1165 |
| LMArena Chinese | 1515 | 1193 |
| LMArena Russian | 1454 | 1195 |
| LMArena French | 1474 | — |
| LMArena German | 1465 | — |
| LMArena Japanese | 1434 | — |
| LMArena Korean | 1418 | — |
| LMArena Spanish | 1469 | — |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), Ministral 8B: 60.5 (#250)
| Benchmark | GLM-5.1 | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1161 |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), Ministral 8B: 36.7 (#227)
| Benchmark | GLM-5.1 | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1466 | 1212 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), Ministral 8B: 39.6 (#246)
| Benchmark | GLM-5.1 | Ministral 8B |
|---|---|---|
| LMArena Text | 1461 | 1191 |
| LMArena Creative Writing | 1453 | 1175 |
| LMArena Multi-Turn | 1472 | 1166 |
| EQ-Bench Creative Writing | 1592 | — |
Frequently asked questions
Is GLM-5.1 better than Ministral 8B?
GLM-5.1 is the stronger model overall, scoring 47.8 to 28.2 on the Noometry Index. Ministral 8B costs 14× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-5.1 or Ministral 8B?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or Ministral 8B better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 35.0 in the Noometry coding category.
Which has the bigger context window?
Ministral 8B does, with 262K tokens against 200K.
How many benchmarks do GLM-5.1 and Ministral 8B share?
13 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Ministral 8B has 17.