Model comparison
GLM-5.3-Flash vs MiniMax-M3
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 43.8 on the Noometry Index.
Last verified . 31 shared benchmarks.
MiniMaxSummary
- They share 31 benchmarks with published results for both. GLM-5.3-Flash scores higher in 9 categories and MiniMax-M3 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.3-Flash leads 48.0 to 30.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.9% for GLM-5.3-Flash and 71.1% for MiniMax-M3.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
Side by side
| GLM-5.3-Flash | MiniMax-M3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | MiniMax |
| Noometry Index | 51.8 | 43.8 |
| Released | 2026-08-20 | 2026-06-01 |
| Weights | Open | Open |
| Context window | 1M | 1M |
| Max output | 131K | 512K |
| Input $ / M tokens | $0.15 | $0.30 |
| Output $ / M tokens | $0.50 | $1.20 |
| Results tracked | 40 | 41 |
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: 53.1 (#31), MiniMax-M3: 41.8 (#118)
| Benchmark | GLM-5.3-Flash | MiniMax-M3 |
|---|---|---|
| FrontierCode | 31.8% | 14.7% |
| LMArena WebDev | 1609 | 1482 |
| SciCode | 51.6% | 47.1% |
| LMArena Coding | 1508 | 1469 |
| ALE-Bench | 303.55 | 640.02 |
| DeepSWE | 63.4% | — |
| CursorBench | 36.8% | — |
| FrontierSWE | 18.1% | — |
Agentic & Tool Use GLM-5.3-Flash leads
GLM-5.3-Flash: 34.2 (#47), MiniMax-M3: 22.6 (#130)
| Benchmark | GLM-5.3-Flash | MiniMax-M3 |
|---|---|---|
| APEX-Agents | 52.8% | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| GDP.pdf | 14% | — |
| Vending-Bench 2 | — | 2,158 |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 48.0 (#42), MiniMax-M3: 30.1 (#87)
| Benchmark | GLM-5.3-Flash | MiniMax-M3 |
|---|---|---|
| CritPt | 15.4% | 3.7% |
| Chess Puzzles | 14% | 14% |
| LMArena Hard Prompts | 1491 | 1447 |
| Mystery Game Puzzles | 8% | 8% |
| Surface Evolver Bench | 52.5% | 55% |
| Epoch Capabilities Index | 151.88 | 146.95 |
| ARC-AGI-2 | 65.8% | — |
| SimpleBench | — | 45.8% |
| NYT Connections (extended) | — | 65.1% |
| ARC-AGI-1 | 91% | — |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Bench to the Future 3 | 0.15 | — |
| ForecastBench | — | 61.4 |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.3 (#47), MiniMax-M3: 40.0 (#95)
| Benchmark | GLM-5.3-Flash | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.9% | 71.1% |
| ProofBench | 21% | 18% |
| LMArena Math | 1500 | 1429 |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
Knowledge Too close to call
GLM-5.3-Flash: 58.4 (#36), MiniMax-M3: 58.4 (#35)
| Benchmark | GLM-5.3-Flash | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 90.2% | 90.9% |
| LMArena Expert | 1513 | 1461 |
Multimodal GLM-5.3-Flash leads
GLM-5.3-Flash: 42.8 (#27), MiniMax-M3: 40.2 (#51)
| Benchmark | GLM-5.3-Flash | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1296 | 1253 |
| LMArena Document | — | 1435 |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.0 (#25), MiniMax-M3: 53.0 (#75)
| Benchmark | GLM-5.3-Flash | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1462 | 1420 |
| LMArena Chinese | 1527 | 1463 |
| LMArena French | 1496 | 1447 |
| LMArena German | 1470 | 1426 |
| LMArena Japanese | 1429 | 1381 |
| LMArena Korean | 1446 | 1372 |
| LMArena Russian | 1469 | 1428 |
| LMArena Spanish | 1471 | 1432 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.5 (#20), MiniMax-M3: 75.5 (#62)
| Benchmark | GLM-5.3-Flash | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1478 | 1433 |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.4 (#39), MiniMax-M3: 44.2 (#72)
| Benchmark | GLM-5.3-Flash | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1482 | 1445 |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.3 (#50), MiniMax-M3: 62.1 (#83)
| Benchmark | GLM-5.3-Flash | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1471 | 1433 |
| LMArena Creative Writing | 1442 | 1404 |
| LMArena Multi-Turn | 1467 | 1442 |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is GLM-5.3-Flash better than MiniMax-M3?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 43.8 on the Noometry Index.
Which is cheaper, GLM-5.3-Flash or MiniMax-M3?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.
Is GLM-5.3-Flash or MiniMax-M3 better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do GLM-5.3-Flash and MiniMax-M3 share?
31 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and MiniMax-M3 has 41.