Model comparison
GLM-5.2 vs Mixtral 8x7B
GLM-5.2 is the stronger model overall, scoring 51.1 to 27.1 on the Noometry Index. Mixtral 8x7B costs 3.1× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. GLM-5.2 scores higher in 8 categories and Mixtral 8x7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.2 leads 57.1 to 11.0.
- The biggest single-benchmark swing is GPQA Diamond: 91.9% for GLM-5.2 and 30.6% for Mixtral 8x7B.
- Mixtral 8x7B is cheaper at $0.70 / $0.70 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GLM-5.2 accepts more context: 1M tokens versus 32K.
Side by side
| GLM-5.2 | Mixtral 8x7B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 51.1 | 27.1 |
| Released | 2026-06-13 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 1M | 32K |
| Max output | 131K | 32K |
| Input $ / M tokens | $1.40 | $0.70 |
| Output $ / M tokens | $4.40 | $0.70 |
| Results tracked | 51 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 51.3 (#41), Mixtral 8x7B: 32.8 (#269)
| Benchmark | GLM-5.2 | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1485 | 1126 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| LMArena WebDev | 1603 | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |
| ALE-Bench | 1,047 | — |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Agentic & Tool Use Not comparable
GLM-5.2: 32.4 (#63), Mixtral 8x7B: —
| Benchmark | GLM-5.2 | Mixtral 8x7B |
|---|---|---|
| APEX-Agents | 45.2% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.3 (#52), Mixtral 8x7B: 18.2 (#285)
| Benchmark | GLM-5.2 | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1480 | 1115 |
| DTBench | 93.6% | 49.6% |
| Epoch Capabilities Index | 151.78 | 118.47 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| NYT Connections (extended) | 74.3% | — |
| ARC-AGI-1 | 77% | — |
| CritPt | 20.9% | — |
| Chess Puzzles | 21% | — |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 19% | — |
| LMCA | 45.8% | — |
| Surface Evolver Bench | 55.6% | — |
| Adversarial NLI | — | 55.2% |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), Mixtral 8x7B: 18.8 (#289)
| Benchmark | GLM-5.2 | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 1482 | 1147 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| OTIS Mock AIME 2024-2025 | 86.4% | — |
| ProofBench | 35% | — |
| Omni-MATH | — | 10.5% |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), Mixtral 8x7B: 11.0 (#301)
| Benchmark | GLM-5.2 | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 91.9% | 30.6% |
| LMArena Expert | 1486 | 1088 |
| SimpleQA Verified | 34.2% | — |
| MMLU-Pro | — | 33.5% |
| GPQA (HELM) | — | 29.6% |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), Mixtral 8x7B: 29.6 (#266)
| Benchmark | GLM-5.2 | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1459 | 1077 |
| LMArena Chinese | 1519 | 1055 |
| LMArena French | 1479 | 1166 |
| LMArena German | 1468 | 1114 |
| LMArena Japanese | 1451 | 931 |
| LMArena Korean | 1445 | 968 |
| LMArena Russian | 1466 | 1090 |
| LMArena Spanish | 1477 | 1111 |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), Mixtral 8x7B: 51.0 (#297)
| Benchmark | GLM-5.2 | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 1465 | 1109 |
| IFEval | — | 57.5% |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), Mixtral 8x7B: 33.4 (#260)
| Benchmark | GLM-5.2 | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1479 | 1103 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), Mixtral 8x7B: 34.2 (#270)
| Benchmark | GLM-5.2 | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1470 | 1132 |
| LMArena Creative Writing | 1462 | 1109 |
| LMArena Multi-Turn | 1469 | 1115 |
| EQ-Bench Creative Writing | 1757 | — |
| WildBench | — | 67.3% |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than Mixtral 8x7B?
GLM-5.2 is the stronger model overall, scoring 51.1 to 27.1 on the Noometry Index. Mixtral 8x7B costs 3.1× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Which is cheaper, GLM-5.2 or Mixtral 8x7B?
Mixtral 8x7B is cheaper. It lists at $0.70 per million input tokens and $0.70 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or Mixtral 8x7B better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 32K.
How many benchmarks do GLM-5.2 and Mixtral 8x7B share?
20 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Mixtral 8x7B has 38.