Model comparison
GLM-5 vs Mixtral 8x7B
GLM-5 is the stronger model overall, scoring 45.9 to 26.8 on the Noometry Index. Mixtral 8x7B costs 2.2× less per token, which makes it the better buy when GLM-5'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 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 leads 52.2 to 11.0.
- The biggest single-benchmark swing is GPQA Diamond: 87.8% for GLM-5 and 30.6% for Mixtral 8x7B.
- Mixtral 8x7B is cheaper at $0.70 / $0.70 per million input/output tokens, against $1 / $3.20 for GLM-5.
- GLM-5 accepts more context: 205K tokens versus 32K.
Side by side
| GLM-5 | Mixtral 8x7B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 45.9 | 26.8 |
| Released | 2026-02-11 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 205K | 32K |
| Max output | 131K | 32K |
| Input $ / M tokens | $1 | $0.70 |
| Output $ / M tokens | $3.20 | $0.70 |
| Results tracked | 45 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#47), Mixtral 8x7B: 32.2 (#265)
| Benchmark | GLM-5 | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1461 | 1127 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 765.62 | — |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Agentic & Tool Use Not comparable
GLM-5: 30.9 (#65), Mixtral 8x7B: —
| Benchmark | GLM-5 | Mixtral 8x7B |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#100), Mixtral 8x7B: 17.4 (#283)
| Benchmark | GLM-5 | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1115 |
| Epoch Capabilities Index | 145.84 | 118.38 |
| 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 | — | 49.6% |
| Adversarial NLI | — | 55.2% |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math GLM-5 leads
GLM-5: 44.8 (#66), Mixtral 8x7B: 17.2 (#284)
| Benchmark | GLM-5 | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 1440 | 1147 |
| MathArena Final-Answer Competitions | 65.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| Omni-MATH | — | 10.5% |
| MATH Level 5 | — | 10% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 74.4% |
Knowledge GLM-5 leads
GLM-5: 52.2 (#59), Mixtral 8x7B: 11.0 (#296)
| Benchmark | GLM-5 | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 87.8% | 30.6% |
| LMArena Expert | 1454 | 1088 |
| MMLU-Pro | — | 33.5% |
| Vectara Hallucination Rate | 10.1% | — |
| GPQA (HELM) | — | 29.6% |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multilingual GLM-5 leads
GLM-5: 53.9 (#57), Mixtral 8x7B: 29.8 (#261)
| Benchmark | GLM-5 | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1430 | 1077 |
| LMArena Chinese | 1511 | 1055 |
| LMArena French | 1455 | 1165 |
| LMArena German | 1445 | 1114 |
| LMArena Japanese | 1416 | 931 |
| LMArena Korean | 1421 | 968 |
| LMArena Russian | 1436 | 1090 |
| LMArena Spanish | 1452 | 1110 |
Instruction Following GLM-5 leads
GLM-5: 75.4 (#64), Mixtral 8x7B: 51.2 (#292)
| Benchmark | GLM-5 | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 1427 | 1110 |
| IFEval | — | 57.5% |
Long Context GLM-5 leads
GLM-5: 44.6 (#58), Mixtral 8x7B: 33.4 (#255)
| Benchmark | GLM-5 | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1446 | 1103 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.2 (#38), Mixtral 8x7B: 34.4 (#265)
| Benchmark | GLM-5 | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1446 | 1132 |
| LMArena Creative Writing | 1438 | 1109 |
| LMArena Multi-Turn | 1456 | 1115 |
| EQ-Bench Creative Writing | 1601 | — |
| WildBench | — | 67.3% |
Frequently asked questions
Is GLM-5 better than Mixtral 8x7B?
GLM-5 is the stronger model overall, scoring 45.9 to 26.8 on the Noometry Index. Mixtral 8x7B costs 2.2× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Which is cheaper, GLM-5 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 lists at $1 and $3.20.
Is GLM-5 or Mixtral 8x7B better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 32.2 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 32K.
How many benchmarks do GLM-5 and Mixtral 8x7B share?
20 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Mixtral 8x7B has 38.