Model comparison
GLM-5 vs Mistral 7B
GLM-5 is the stronger model overall, scoring 46.1 to 23.0 on the Noometry Index. Mistral 7B costs 6.2× 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 Mistral 7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 7.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 0.3% for Mistral 7B.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $1 / $3.20 for GLM-5.
- GLM-5 accepts more context: 205K tokens versus 8K.
Side by side
| GLM-5 | Mistral 7B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 46.1 | 23.0 |
| Released | 2026-02-11 | 2023-09-27 |
| Weights | Open | Open |
| Context window | 205K | 8K |
| Max output | 131K | 8K |
| Input $ / M tokens | $1 | $0.25 |
| Output $ / M tokens | $3.20 | $0.25 |
| Results tracked | 45 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Mistral 7B: 26.4 (#326)
| Benchmark | GLM-5 | Mistral 7B |
|---|---|---|
| LMArena Coding | 1461 | 1082 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| WeirdML | 48.2% | — |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| ALE-Bench | 765.62 | — |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), Mistral 7B: —
| Benchmark | GLM-5 | Mistral 7B |
|---|---|---|
| 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 (#116), Mistral 7B: 13.1 (#336)
| Benchmark | GLM-5 | Mistral 7B |
|---|---|---|
| Chess Puzzles | 10% | 0% |
| LMArena Hard Prompts | 1452 | 1067 |
| Epoch Capabilities Index | 145.83 | 112.21 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| ForecastBench | 61 | — |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math GLM-5 leads
GLM-5: 46.4 (#71), Mistral 7B: 8.1 (#325)
| Benchmark | GLM-5 | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 0.3% |
| LMArena Math | 1440 | 1085 |
| MathArena Final-Answer Competitions | 65.7% | — |
| MATH Level 5 | — | 3.7% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 54.4% |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), Mistral 7B: 7.4 (#311)
| Benchmark | GLM-5 | Mistral 7B |
|---|---|---|
| GPQA Diamond | 87.8% | 15.2% |
| LMArena Expert | 1454 | 1036 |
| Vectara Hallucination Rate | 10.1% | — |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), Mistral 7B: 25.8 (#283)
| Benchmark | GLM-5 | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1430 | 1012 |
| LMArena Chinese | 1511 | 1009 |
| LMArena French | 1455 | 1037 |
| LMArena German | 1445 | 987 |
| LMArena Japanese | 1416 | 878 |
| LMArena Russian | 1436 | 1018 |
| LMArena Spanish | 1454 | 1026 |
| LMArena Korean | 1423 | — |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), Mistral 7B: 54.2 (#280)
| Benchmark | GLM-5 | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1428 | 1060 |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), Mistral 7B: 32.2 (#271)
| Benchmark | GLM-5 | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1446 | 1060 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Mistral 7B: 30.7 (#286)
| Benchmark | GLM-5 | Mistral 7B |
|---|---|---|
| LMArena Text | 1446 | 1090 |
| LMArena Creative Writing | 1439 | 1068 |
| LMArena Multi-Turn | 1456 | 1062 |
| EQ-Bench Creative Writing | 1601 | — |
Frequently asked questions
Is GLM-5 better than Mistral 7B?
GLM-5 is the stronger model overall, scoring 46.1 to 23.0 on the Noometry Index. Mistral 7B costs 6.2× 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 Mistral 7B?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; GLM-5 lists at $1 and $3.20.
Is GLM-5 or Mistral 7B better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 8K.
How many benchmarks do GLM-5 and Mistral 7B share?
20 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Mistral 7B has 37.