Model comparison
GLM-5 vs Mistral Small 3.1
GLM-5 is the stronger model overall, scoring 46.1 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 3.9× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. GLM-5 scores higher in 8 categories and Mistral Small 3.1 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5 leads 46.4 to 14.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 3.9% for Mistral Small 3.1.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $1 / $3.20 for GLM-5.
- GLM-5 accepts more context: 205K tokens versus 128K.
Side by side
| GLM-5 | Mistral Small 3.1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 46.1 | 31.7 |
| Released | 2026-02-11 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 205K | 128K |
| Max output | 131K | 102K |
| Input $ / M tokens | $1 | $0.35 |
| Output $ / M tokens | $3.20 | $0.56 |
| Results tracked | 45 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Mistral Small 3.1: 38.3 (#179)
| Benchmark | GLM-5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1461 | 1309 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), Mistral Small 3.1: —
| Benchmark | GLM-5 | Mistral Small 3.1 |
|---|---|---|
| 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), Mistral Small 3.1: 19.7 (#254)
| Benchmark | GLM-5 | Mistral Small 3.1 |
|---|---|---|
| Chess Puzzles | 10% | 1% |
| LMArena Hard Prompts | 1452 | 1278 |
| Epoch Capabilities Index | 145.83 | 127.48 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| ForecastBench | 61 | — |
Math GLM-5 leads
GLM-5: 46.4 (#71), Mistral Small 3.1: 14.7 (#301)
| Benchmark | GLM-5 | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 3.9% |
| LMArena Math | 1440 | 1262 |
| MathArena Final-Answer Competitions | 65.7% | — |
| Omni-MATH | — | 24.8% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), Mistral Small 3.1: 22.6 (#271)
| Benchmark | GLM-5 | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 87.8% | 41.9% |
| LMArena Expert | 1454 | 1257 |
| MMLU-Pro | — | 61% |
| Vectara Hallucination Rate | 10.1% | — |
| GPQA (HELM) | — | 39.2% |
Multimodal Not comparable
GLM-5: —, Mistral Small 3.1: 33.2 (#99)
| Benchmark | GLM-5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), Mistral Small 3.1: 41.2 (#209)
| Benchmark | GLM-5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1430 | 1255 |
| LMArena Chinese | 1511 | 1253 |
| LMArena French | 1455 | 1273 |
| LMArena German | 1445 | 1266 |
| LMArena Japanese | 1416 | 1208 |
| LMArena Korean | 1423 | 1206 |
| LMArena Russian | 1436 | 1263 |
| LMArena Spanish | 1454 | 1283 |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), Mistral Small 3.1: 63.6 (#230)
| Benchmark | GLM-5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1428 | 1264 |
| IFEval | — | 75% |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), Mistral Small 3.1: 39.5 (#178)
| Benchmark | GLM-5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1446 | 1299 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Mistral Small 3.1: 37.0 (#259)
| Benchmark | GLM-5 | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1446 | 1277 |
| LMArena Creative Writing | 1439 | 1253 |
| EQ-Bench Creative Writing | 1601 | 761 |
| LMArena Multi-Turn | 1456 | 1270 |
| WildBench | — | 78.8% |
Frequently asked questions
Is GLM-5 better than Mistral Small 3.1?
GLM-5 is the stronger model overall, scoring 46.1 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 3.9× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Which is cheaper, GLM-5 or Mistral Small 3.1?
Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; GLM-5 lists at $1 and $3.20.
Is GLM-5 or Mistral Small 3.1 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 38.3 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 128K.
How many benchmarks do GLM-5 and Mistral Small 3.1 share?
22 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Mistral Small 3.1 has 28.