Model comparison
GLM-4.6 vs Mistral Large 3
GLM-4.6 is the stronger model overall, scoring 41.4 to 39.1 on the Noometry Index. Mistral Large 3 costs 2.7× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. GLM-4.6 scores higher in 8 categories and Mistral Large 3 in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.6 leads 23.7 to 15.2.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 9.5% for GLM-4.6 and 14.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- Mistral Large 3 accepts more context: 262K tokens versus 205K.
Side by side
| GLM-4.6 | Mistral Large 3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 41.4 | 39.1 |
| Released | 2025-09-30 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.60 | $0.25 |
| Output $ / M tokens | $2.20 | $0.75 |
| Results tracked | 29 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 40.1 (#148), Mistral Large 3: 34.4 (#237)
| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1340 | 1230 |
| LMArena Coding | 1449 | 1448 |
| SWE-bench Verified (bash only) | 55.4% | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use Not comparable
GLM-4.6: 32.3 (#66), Mistral Large 3: —
| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning GLM-4.6 leads
GLM-4.6: 23.7 (#172), Mistral Large 3: 15.2 (#319)
| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 50.9% |
| LMArena Hard Prompts | 1440 | 1429 |
| NYT Connections (extended) | — | 7.5% |
| CritPt | 1.1% | — |
| Thematic Generalization | — | 23% |
Math Too close to call
GLM-4.6: 39.1 (#111), Mistral Large 3: 38.7 (#129)
| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1432 | 1414 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-4.6 leads
GLM-4.6: 40.2 (#124), Mistral Large 3: 36.0 (#177)
| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 14.5% |
| LMArena Expert | 1431 | 1421 |
Multimodal Not comparable
GLM-4.6: —, Mistral Large 3: 38.2 (#66)
| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Too close to call
GLM-4.6: 53.5 (#66), Mistral Large 3: 52.5 (#84)
| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1426 | 1413 |
| LMArena Chinese | 1499 | 1447 |
| LMArena French | 1459 | 1455 |
| LMArena German | 1447 | 1437 |
| LMArena Japanese | 1393 | 1394 |
| LMArena Korean | 1400 | 1384 |
| LMArena Russian | 1419 | 1411 |
| LMArena Spanish | 1436 | 1440 |
Instruction Following Too close to call
GLM-4.6: 74.3 (#98), Mistral Large 3: 74.0 (#108)
| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1403 |
Long Context Too close to call
GLM-4.6: 43.4 (#94), Mistral Large 3: 43.1 (#105)
| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1422 | 1413 |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.1 (#90), Mistral Large 3: 60.0 (#101)
| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1440 | 1428 |
| LMArena Creative Writing | 1411 | 1386 |
| EQ-Bench Creative Writing | 1411 | 1412 |
| LMArena Multi-Turn | 1427 | 1429 |
Frequently asked questions
Is GLM-4.6 better than Mistral Large 3?
GLM-4.6 is the stronger model overall, scoring 41.4 to 39.1 on the Noometry Index. Mistral Large 3 costs 2.7× 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 Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or Mistral Large 3 better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 205K.
How many benchmarks do GLM-4.6 and Mistral Large 3 share?
21 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Mistral Large 3 has 24.