Model comparison
GLM-5.2 vs Mistral Medium
GLM-5.2 is the stronger model overall, scoring 51.1 to 36.3 on the Noometry Index.
Last verified . 29 shared benchmarks.
Mistral AISummary
- They share 29 benchmarks with published results for both. GLM-5.2 scores higher in 9 categories and Mistral Medium in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.2 leads 57.1 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.4% for GLM-5.2 and 32.2% for Mistral Medium.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- GLM-5.2 accepts more context: 1M tokens versus 262K.
Side by side
| GLM-5.2 | Mistral Medium | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 51.1 | 36.3 |
| Released | 2026-06-13 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $1.40 | $1.50 |
| Output $ / M tokens | $4.40 | $7.50 |
| Results tracked | 51 | 36 |
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), Mistral Medium: 34.2 (#243)
| Benchmark | GLM-5.2 | Mistral Medium |
|---|---|---|
| FrontierCode | 24.5% | 8% |
| SciCode | 50.5% | 40.2% |
| WeirdML | 70.1% | 43.7% |
| LMArena Coding | 1485 | 1434 |
| ALE-Bench | 1,047 | 763.98 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| LMArena WebDev | 1603 | — |
Agentic & Tool Use GLM-5.2 leads
GLM-5.2: 32.4 (#63), Mistral Medium: 28.3 (#90)
| Benchmark | GLM-5.2 | Mistral Medium |
|---|---|---|
| APEX-Agents | 45.2% | — |
| Berkeley Function Calling Leaderboard | — | 37.7% |
| 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), Mistral Medium: 24.0 (#167)
| Benchmark | GLM-5.2 | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 62.6% | 50% |
| CritPt | 20.9% | 0% |
| LMArena Hard Prompts | 1480 | 1426 |
| DTBench | 93.6% | 75.5% |
| LMCA | 45.8% | 26.1% |
| Surface Evolver Bench | 55.6% | 26.9% |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| NYT Connections (extended) | 74.3% | — |
| ARC-AGI-1 | 77% | — |
| Chess Puzzles | 21% | — |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 19% | — |
| Epoch Capabilities Index | 151.78 | — |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), Mistral Medium: 28.1 (#245)
| Benchmark | GLM-5.2 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.4% | 32.2% |
| ProofBench | 35% | 9% |
| LMArena Math | 1482 | 1408 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), Mistral Medium: 25.0 (#265)
| Benchmark | GLM-5.2 | Mistral Medium |
|---|---|---|
| GPQA Diamond | 91.9% | 59.5% |
| LMArena Expert | 1486 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 34.2% | — |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Not comparable
GLM-5.2: —, Mistral Medium: 35.3 (#88)
| Benchmark | GLM-5.2 | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), Mistral Medium: 52.1 (#91)
| Benchmark | GLM-5.2 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1459 | 1408 |
| LMArena Chinese | 1519 | 1447 |
| LMArena French | 1479 | 1459 |
| LMArena German | 1468 | 1432 |
| LMArena Japanese | 1451 | 1378 |
| LMArena Korean | 1445 | 1380 |
| LMArena Russian | 1466 | 1411 |
| LMArena Spanish | 1477 | 1433 |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), Mistral Medium: 73.7 (#116)
| Benchmark | GLM-5.2 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1465 | 1398 |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), Mistral Medium: 42.9 (#114)
| Benchmark | GLM-5.2 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1479 | 1406 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), Mistral Medium: 60.0 (#103)
| Benchmark | GLM-5.2 | Mistral Medium |
|---|---|---|
| LMArena Text | 1470 | 1424 |
| LMArena Creative Writing | 1462 | 1391 |
| LMArena Multi-Turn | 1469 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than Mistral Medium?
GLM-5.2 is the stronger model overall, scoring 51.1 to 36.3 on the Noometry Index.
Which is cheaper, GLM-5.2 or Mistral Medium?
GLM-5.2 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is GLM-5.2 or Mistral Medium better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 262K.
How many benchmarks do GLM-5.2 and Mistral Medium share?
29 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Mistral Medium has 36.