Model comparison
GLM-4.6 vs Mistral Small
GLM-4.6 is the stronger model overall, scoring 40.9 to 33.1 on the Noometry Index. Mistral Small costs 3.8× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Mistral AISummary
- They share 23 benchmarks with published results for both. GLM-4.6 scores higher in 9 categories and Mistral Small in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.6 leads 36.4 to 15.4.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 72.4% for GLM-4.6 and 37.1% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- Mistral Small accepts more context: 256K tokens versus 205K.
Side by side
| GLM-4.6 | Mistral Small | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 40.9 | 33.1 |
| Released | 2025-09-30 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 205K | 256K |
| Max output | 131K | 256K |
| Input $ / M tokens | $0.60 | $0.15 |
| Output $ / M tokens | $2.20 | $0.60 |
| Results tracked | 29 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 39.9 (#137), Mistral Small: 33.5 (#242)
| Benchmark | GLM-4.6 | Mistral Small |
|---|---|---|
| SciCode | 38.4% | 26.5% |
| LMArena Coding | 1449 | 1363 |
| ALE-Bench | 340.82 | 497.62 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1339 | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.1 (#60), Mistral Small: 27.9 (#87)
| Benchmark | GLM-4.6 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 72.4% | 37.1% |
| Terminal-Bench | 24.5% | — |
Reasoning GLM-4.6 leads
GLM-4.6: 23.1 (#168), Mistral Small: 19.3 (#238)
| Benchmark | GLM-4.6 | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 37.8% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1440 | 1336 |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |
Math GLM-4.6 leads
GLM-4.6: 36.4 (#115), Mistral Small: 15.4 (#287)
| Benchmark | GLM-4.6 | Mistral Small |
|---|---|---|
| LMArena Math | 1431 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-4.6 leads
GLM-4.6: 39.6 (#118), Mistral Small: 30.9 (#214)
| Benchmark | GLM-4.6 | Mistral Small |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 5.1% |
| LMArena Expert | 1432 | 1293 |
| GPQA Diamond | — | 47.5% |
| MMLU | — | 68.7% |
Multimodal Not comparable
GLM-4.6: —, Mistral Small: 32.9 (#91)
| Benchmark | GLM-4.6 | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual GLM-4.6 leads
GLM-4.6: 53.6 (#62), Mistral Small: 45.7 (#164)
| Benchmark | GLM-4.6 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1426 | 1315 |
| LMArena Chinese | 1500 | 1342 |
| LMArena French | 1459 | 1337 |
| LMArena German | 1447 | 1341 |
| LMArena Japanese | 1394 | 1275 |
| LMArena Korean | 1401 | 1260 |
| LMArena Russian | 1418 | 1324 |
| LMArena Spanish | 1436 | 1346 |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.5 (#93), Mistral Small: 66.6 (#204)
| Benchmark | GLM-4.6 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1410 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#91), Mistral Small: 40.4 (#151)
| Benchmark | GLM-4.6 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1423 | 1327 |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.3 (#86), Mistral Small: 52.6 (#165)
| Benchmark | GLM-4.6 | Mistral Small |
|---|---|---|
| LMArena Text | 1440 | 1338 |
| LMArena Creative Writing | 1411 | 1304 |
| LMArena Multi-Turn | 1427 | 1344 |
| EQ-Bench Creative Writing | 1411 | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is GLM-4.6 better than Mistral Small?
GLM-4.6 is the stronger model overall, scoring 40.9 to 33.1 on the Noometry Index. Mistral Small costs 3.8× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6 or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or Mistral Small better for coding?
GLM-4.6 scores higher on coding benchmarks: 39.9 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 256K tokens against 205K.
How many benchmarks do GLM-4.6 and Mistral Small share?
23 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Mistral Small has 39.