Model comparison
GLM-5.3-Flash vs Mistral Medium
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 36.0 on the Noometry Index.
Last verified . 26 shared benchmarks.
Mistral AISummary
- They share 26 benchmarks with published results for both. GLM-5.3-Flash scores higher in 10 categories and Mistral Medium in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.3-Flash leads 58.4 to 24.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.9% for GLM-5.3-Flash and 32.2% for Mistral Medium.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- GLM-5.3-Flash accepts more context: 1M tokens versus 262K.
Side by side
| GLM-5.3-Flash | Mistral Medium | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 49.6 | 36.0 |
| Released | 2026-08-20 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $0.15 | $1.50 |
| Output $ / M tokens | $0.50 | $7.50 |
| Results tracked | 36 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
GLM-5.3-Flash: 53.7 (#26), Mistral Medium: 33.8 (#241)
| Benchmark | GLM-5.3-Flash | Mistral Medium |
|---|---|---|
| FrontierCode | 31.8% | 8% |
| SciCode | 51.6% | 40.2% |
| LMArena Coding | 1506 | 1434 |
| ALE-Bench | 303.55 | 763.98 |
| DeepSWE | 63.4% | — |
| LMArena WebDev | 1614 | — |
| WeirdML | — | 43.7% |
Agentic & Tool Use GLM-5.3-Flash leads
GLM-5.3-Flash: 34.3 (#41), Mistral Medium: 28.1 (#84)
| Benchmark | GLM-5.3-Flash | Mistral Medium |
|---|---|---|
| APEX-Agents | 52.8% | — |
| Berkeley Function Calling Leaderboard | — | 37.7% |
| GDP.pdf | 14% | — |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 31.7 (#69), Mistral Medium: 23.3 (#165)
| Benchmark | GLM-5.3-Flash | Mistral Medium |
|---|---|---|
| CritPt | 15.4% | 0% |
| LMArena Hard Prompts | 1490 | 1426 |
| Surface Evolver Bench | 52.5% | 26.9% |
| Kagi LLM Benchmark | — | 50% |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Bench to the Future 3 | 0.15 | — |
| Epoch Capabilities Index | 151.9 | — |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.1 (#38), Mistral Medium: 27.2 (#238)
| Benchmark | GLM-5.3-Flash | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.9% | 32.2% |
| ProofBench | 21% | 9% |
| LMArena Math | 1499 | 1409 |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#33), Mistral Medium: 24.9 (#260)
| Benchmark | GLM-5.3-Flash | Mistral Medium |
|---|---|---|
| GPQA Diamond | 90.2% | 59.5% |
| LMArena Expert | 1512 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal GLM-5.3-Flash leads
GLM-5.3-Flash: 42.6 (#25), Mistral Medium: 34.6 (#82)
| Benchmark | GLM-5.3-Flash | Mistral Medium |
|---|---|---|
| LMArena Vision | 1304 | 1172 |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.2 (#24), Mistral Medium: 52.3 (#86)
| Benchmark | GLM-5.3-Flash | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1462 | 1408 |
| LMArena Chinese | 1529 | 1448 |
| LMArena French | 1495 | 1460 |
| LMArena German | 1457 | 1433 |
| LMArena Japanese | 1420 | 1378 |
| LMArena Korean | 1443 | 1382 |
| LMArena Russian | 1472 | 1411 |
| LMArena Spanish | 1471 | 1433 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.8 (#17), Mistral Medium: 73.9 (#111)
| Benchmark | GLM-5.3-Flash | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1480 | 1398 |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.3 (#41), Mistral Medium: 42.9 (#108)
| Benchmark | GLM-5.3-Flash | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1479 | 1406 |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.4 (#49), Mistral Medium: 60.2 (#97)
| Benchmark | GLM-5.3-Flash | Mistral Medium |
|---|---|---|
| LMArena Text | 1471 | 1424 |
| LMArena Creative Writing | 1440 | 1391 |
| LMArena Multi-Turn | 1471 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
Frequently asked questions
Is GLM-5.3-Flash better than Mistral Medium?
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 36.0 on the Noometry Index.
Which is cheaper, GLM-5.3-Flash or Mistral Medium?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is GLM-5.3-Flash or Mistral Medium better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 262K.
How many benchmarks do GLM-5.3-Flash and Mistral Medium share?
26 benchmarks have published results for both models. GLM-5.3-Flash has 36 scored results on Noometry and Mistral Medium has 36.