Model comparison
GLM-5 vs Mixtral 8x22B
GLM-5 is the stronger model overall, scoring 46.1 to 27.1 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. GLM-5 scores higher in 9 categories and Mixtral 8x22B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 15.1.
- The biggest single-benchmark swing is GPQA Diamond: 87.8% for GLM-5 and 34.1% for Mixtral 8x22B.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- GLM-5 accepts more context: 205K tokens versus 64K.
Side by side
| GLM-5 | Mixtral 8x22B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 46.1 | 27.1 |
| Released | 2026-02-11 | 2024-04-17 |
| Weights | Open | Open |
| Context window | 205K | 64K |
| Max output | 131K | 64K |
| Input $ / M tokens | $1 | $2 |
| Output $ / M tokens | $3.20 | $6 |
| Results tracked | 45 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Mixtral 8x22B: 24.2 (#329)
| Benchmark | GLM-5 | Mixtral 8x22B |
|---|---|---|
| WeirdML | 48.2% | 3.2% |
| LMArena Coding | 1461 | 1166 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 765.62 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use GLM-5 leads
GLM-5: 31.1 (#71), Mixtral 8x22B: 23.1 (#127)
| Benchmark | GLM-5 | Mixtral 8x22B |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Cybench | — | 7.5% |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#116), Mixtral 8x22B: 19.9 (#248)
| Benchmark | GLM-5 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1150 |
| Epoch Capabilities Index | 145.83 | 122.03 |
| ForecastBench | 61 | 56.3 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| Chess Puzzles | 10% | — |
| DTBench | — | 55.1% |
Math GLM-5 leads
GLM-5: 46.4 (#71), Mixtral 8x22B: 22.9 (#275)
| Benchmark | GLM-5 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1440 | 1184 |
| MathArena Final-Answer Competitions | 65.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), Mixtral 8x22B: 15.1 (#293)
| Benchmark | GLM-5 | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 87.8% | 34.1% |
| LMArena Expert | 1454 | 1113 |
| MMLU-Pro | — | 46% |
| Vectara Hallucination Rate | 10.1% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), Mixtral 8x22B: 32.8 (#255)
| Benchmark | GLM-5 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1430 | 1128 |
| LMArena Chinese | 1511 | 1116 |
| LMArena French | 1455 | 1166 |
| LMArena German | 1445 | 1141 |
| LMArena Japanese | 1416 | 1037 |
| LMArena Korean | 1423 | 1057 |
| LMArena Russian | 1436 | 1158 |
| LMArena Spanish | 1454 | 1151 |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), Mixtral 8x22B: 57.7 (#266)
| Benchmark | GLM-5 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1428 | 1147 |
| IFEval | — | 72.4% |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), Mixtral 8x22B: 34.7 (#247)
| Benchmark | GLM-5 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1446 | 1144 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Mixtral 8x22B: 36.9 (#262)
| Benchmark | GLM-5 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1446 | 1162 |
| LMArena Creative Writing | 1439 | 1141 |
| LMArena Multi-Turn | 1456 | 1130 |
| EQ-Bench Creative Writing | 1601 | — |
| WildBench | — | 71.1% |
Frequently asked questions
Is GLM-5 better than Mixtral 8x22B?
GLM-5 is the stronger model overall, scoring 46.1 to 27.1 on the Noometry Index.
Which is cheaper, GLM-5 or Mixtral 8x22B?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is GLM-5 or Mixtral 8x22B better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 64K.
How many benchmarks do GLM-5 and Mixtral 8x22B share?
21 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Mixtral 8x22B has 34.