Model comparison
GLM-5.2 vs Mistral Large
GLM-5.2 is the stronger model overall, scoring 50.9 to 31.6 on the Noometry Index.
Last verified . 27 shared benchmarks.
Mistral AISummary
- They share 27 benchmarks with published results for both. GLM-5.2 scores higher in 9 categories and Mistral Large in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.4 to 17.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.4% for GLM-5.2 and 8.5% for Mistral Large.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $2 / $6 for Mistral Large.
- GLM-5.2 accepts more context: 1M tokens versus 131K.
Side by side
| GLM-5.2 | Mistral Large | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 50.9 | 31.6 |
| Released | 2026-06-13 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 1M | 131K |
| Max output | 131K | 16K |
| Input $ / M tokens | $1.40 | $2 |
| Output $ / M tokens | $4.40 | $6 |
| Results tracked | 50 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 50.9 (#37), Mistral Large: 33.8 (#240)
| Benchmark | GLM-5.2 | Mistral Large |
|---|---|---|
| SciCode | 50.5% | 36.2% |
| LMArena Coding | 1484 | 1277 |
| ALE-Bench | 1,047 | 264.7 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| LMArena WebDev | 1604 | — |
| WeirdML | 70.1% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use GLM-5.2 leads
GLM-5.2: 31.6 (#63), Mistral Large: 28.4 (#83)
| Benchmark | GLM-5.2 | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.1 (#46), Mistral Large: 15.4 (#305)
| Benchmark | GLM-5.2 | Mistral Large |
|---|---|---|
| SimpleBench | 58.8% | 22.5% |
| CritPt | 20.9% | 0% |
| LMArena Hard Prompts | 1480 | 1257 |
| DTBench | 93.6% | 65.1% |
| LMCA | 45.8% | 16.7% |
| Epoch Capabilities Index | 151.76 | 128.52 |
| ARC-AGI-2 | 22.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| NYT Connections (extended) | 74.3% | — |
| ARC-AGI-1 | 77% | — |
| Chess Puzzles | 21% | — |
| EBR-Bench | 9.5% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 19% | — |
| LiveBench Data Analysis | — | 50.1% |
| Surface Evolver Bench | 55.6% | — |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math GLM-5.2 leads
GLM-5.2: 55.4 (#35), Mistral Large: 17.1 (#285)
| Benchmark | GLM-5.2 | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.4% | 8.5% |
| LMArena Math | 1482 | 1262 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 35% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#36), Mistral Large: 30.0 (#224)
| Benchmark | GLM-5.2 | Mistral Large |
|---|---|---|
| GPQA Diamond | 91.9% | 51.3% |
| LMArena Expert | 1484 | 1232 |
| SimpleQA Verified | 34.2% | — |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multilingual GLM-5.2 leads
GLM-5.2: 56.0 (#25), Mistral Large: 40.1 (#214)
| Benchmark | GLM-5.2 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1459 | 1237 |
| LMArena Chinese | 1518 | 1240 |
| LMArena French | 1476 | 1324 |
| LMArena German | 1470 | 1254 |
| LMArena Japanese | 1451 | 1187 |
| LMArena Korean | 1445 | 1202 |
| LMArena Russian | 1467 | 1257 |
| LMArena Spanish | 1477 | 1268 |
Instruction Following GLM-5.2 leads
GLM-5.2: 77.1 (#32), Mistral Large: 68.1 (#186)
| Benchmark | GLM-5.2 | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1465 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), Mistral Large: 38.3 (#194)
| Benchmark | GLM-5.2 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1479 | 1262 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.7 (#20), Mistral Large: 40.9 (#237)
| Benchmark | GLM-5.2 | Mistral Large |
|---|---|---|
| LMArena Text | 1470 | 1266 |
| LMArena Creative Writing | 1465 | 1243 |
| EQ-Bench Creative Writing | 1757 | 985 |
| LMArena Multi-Turn | 1468 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| EQ-Bench 4 | 1222 | — |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is GLM-5.2 better than Mistral Large?
GLM-5.2 is the stronger model overall, scoring 50.9 to 31.6 on the Noometry Index.
Which is cheaper, GLM-5.2 or Mistral Large?
GLM-5.2 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Mistral Large lists at $2 and $6.
Is GLM-5.2 or Mistral Large better for coding?
GLM-5.2 scores higher on coding benchmarks: 50.9 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 131K.
How many benchmarks do GLM-5.2 and Mistral Large share?
27 benchmarks have published results for both models. GLM-5.2 has 50 scored results on Noometry and Mistral Large has 51.