Model comparison
GLM-4.6 vs Mistral Medium
GLM-4.6 is the stronger model overall, scoring 40.9 to 36.0 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AISummary
- They share 24 benchmarks with published results for both. GLM-4.6 scores higher in 8 categories and Mistral Medium in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.6 leads 39.6 to 24.9.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 72.4% for GLM-4.6 and 37.7% for Mistral Medium.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 205K.
Side by side
| GLM-4.6 | Mistral Medium | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 40.9 | 36.0 |
| Released | 2025-09-30 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $0.60 | $1.50 |
| Output $ / M tokens | $2.20 | $7.50 |
| Results tracked | 29 | 36 |
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 Medium: 33.8 (#241)
| Benchmark | GLM-4.6 | Mistral Medium |
|---|---|---|
| SciCode | 38.4% | 40.2% |
| LMArena Coding | 1449 | 1434 |
| ALE-Bench | 340.82 | 763.98 |
| FrontierCode | — | 8% |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1339 | — |
| WeirdML | — | 43.7% |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.1 (#60), Mistral Medium: 28.1 (#84)
| Benchmark | GLM-4.6 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 72.4% | 37.7% |
| Terminal-Bench | 24.5% | — |
Reasoning Too close to call
GLM-4.6: 23.1 (#168), Mistral Medium: 23.3 (#165)
| Benchmark | GLM-4.6 | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 50% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1440 | 1426 |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math GLM-4.6 leads
GLM-4.6: 36.4 (#115), Mistral Medium: 27.2 (#238)
| Benchmark | GLM-4.6 | Mistral Medium |
|---|---|---|
| LMArena Math | 1431 | 1409 |
| FrontierMath (Feb 2025 set) | 3.8% | 0.3% |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-4.6 leads
GLM-4.6: 39.6 (#118), Mistral Medium: 24.9 (#260)
| Benchmark | GLM-4.6 | Mistral Medium |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 22.7% |
| LMArena Expert | 1432 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
Multimodal Not comparable
GLM-4.6: —, Mistral Medium: 34.6 (#82)
| Benchmark | GLM-4.6 | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual GLM-4.6 leads
GLM-4.6: 53.6 (#62), Mistral Medium: 52.3 (#86)
| Benchmark | GLM-4.6 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1426 | 1408 |
| LMArena Chinese | 1500 | 1448 |
| LMArena French | 1459 | 1460 |
| LMArena German | 1447 | 1433 |
| LMArena Japanese | 1394 | 1378 |
| LMArena Korean | 1401 | 1382 |
| LMArena Russian | 1418 | 1411 |
| LMArena Spanish | 1436 | 1433 |
Instruction Following Too close to call
GLM-4.6: 74.5 (#93), Mistral Medium: 73.9 (#111)
| Benchmark | GLM-4.6 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1410 | 1398 |
Long Context Too close to call
GLM-4.6: 43.4 (#91), Mistral Medium: 42.9 (#108)
| Benchmark | GLM-4.6 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1423 | 1406 |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.3 (#86), Mistral Medium: 60.2 (#97)
| Benchmark | GLM-4.6 | Mistral Medium |
|---|---|---|
| LMArena Text | 1440 | 1424 |
| LMArena Creative Writing | 1411 | 1391 |
| LMArena Multi-Turn | 1427 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Mistral Medium?
GLM-4.6 is the stronger model overall, scoring 40.9 to 36.0 on the Noometry Index.
Which is cheaper, GLM-4.6 or Mistral Medium?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is GLM-4.6 or Mistral Medium better for coding?
GLM-4.6 scores higher on coding benchmarks: 39.9 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 205K.
How many benchmarks do GLM-4.6 and Mistral Medium share?
24 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Mistral Medium has 36.