Model comparison
GLM-4.7 vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.8 to 42.0 on the Noometry Index.
Last verified . 28 shared benchmarks.
MiniMaxSummary
- They share 28 benchmarks with published results for both. GLM-4.7 scores higher in 2 categories and MiniMax-M3 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 47.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 71.1% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- MiniMax-M3 accepts more context: 1M tokens versus 205K.
Side by side
| GLM-4.7 | MiniMax-M3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | MiniMax |
| Noometry Index | 42.0 | 43.8 |
| Released | 2025-12-22 | 2026-06-01 |
| Weights | Open | Open |
| Context window | 205K | 1M |
| Max output | 131K | 512K |
| Input $ / M tokens | $0.60 | $0.30 |
| Output $ / M tokens | $2.20 | $1.20 |
| Results tracked | 36 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
GLM-4.7: 44.0 (#79), MiniMax-M3: 41.8 (#118)
| Benchmark | GLM-4.7 | MiniMax-M3 |
|---|---|---|
| LMArena WebDev | 1435 | 1482 |
| SciCode | 45.1% | 47.1% |
| LMArena Coding | 1454 | 1469 |
| ALE-Bench | 399.48 | 640.02 |
| FrontierCode | — | 14.7% |
Agentic & Tool Use GLM-4.7 leads
GLM-4.7: 26.5 (#103), MiniMax-M3: 22.6 (#130)
| Benchmark | GLM-4.7 | MiniMax-M3 |
|---|---|---|
| Vending-Bench 2 | 2,377 | 2,158 |
| Terminal-Bench | 33.4% | — |
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
Reasoning MiniMax-M3 leads
GLM-4.7: 24.3 (#164), MiniMax-M3: 30.1 (#87)
| Benchmark | GLM-4.7 | MiniMax-M3 |
|---|---|---|
| SimpleBench | 47.7% | 45.8% |
| CritPt | 1.7% | 3.7% |
| Chess Puzzles | 6% | 14% |
| LMArena Hard Prompts | 1443 | 1447 |
| Epoch Capabilities Index | 143.51 | 146.95 |
| NYT Connections (extended) | — | 65.1% |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |
Math MiniMax-M3 leads
GLM-4.7: 38.6 (#135), MiniMax-M3: 40.0 (#95)
| Benchmark | GLM-4.7 | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 71.1% |
| ProofBench | 6% | 18% |
| LMArena Math | 1423 | 1429 |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge MiniMax-M3 leads
GLM-4.7: 47.0 (#80), MiniMax-M3: 58.4 (#35)
| Benchmark | GLM-4.7 | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 83.3% | 90.9% |
| LMArena Expert | 1424 | 1461 |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |
Multimodal Not comparable
GLM-4.7: —, MiniMax-M3: 40.2 (#51)
| Benchmark | GLM-4.7 | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |
Multilingual Too close to call
GLM-4.7: 52.8 (#79), MiniMax-M3: 53.0 (#75)
| Benchmark | GLM-4.7 | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1417 | 1420 |
| LMArena Chinese | 1495 | 1463 |
| LMArena French | 1432 | 1447 |
| LMArena German | 1424 | 1426 |
| LMArena Japanese | 1439 | 1381 |
| LMArena Korean | 1399 | 1372 |
| LMArena Russian | 1423 | 1428 |
| LMArena Spanish | 1434 | 1432 |
Instruction Following MiniMax-M3 leads
GLM-4.7: 74.4 (#95), MiniMax-M3: 75.5 (#62)
| Benchmark | GLM-4.7 | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1411 | 1433 |
Long Context MiniMax-M3 leads
GLM-4.7: 42.8 (#116), MiniMax-M3: 44.2 (#72)
| Benchmark | GLM-4.7 | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1432 | 1445 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference MiniMax-M3 leads
GLM-4.7: 60.9 (#93), MiniMax-M3: 62.1 (#83)
| Benchmark | GLM-4.7 | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1435 | 1433 |
| LMArena Creative Writing | 1401 | 1404 |
| LMArena Multi-Turn | 1446 | 1442 |
| EQ-Bench Creative Writing | 1413 | — |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is GLM-4.7 better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 42.0 on the Noometry Index.
Which is cheaper, GLM-4.7 or MiniMax-M3?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.
Is GLM-4.7 or MiniMax-M3 better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 205K.
How many benchmarks do GLM-4.7 and MiniMax-M3 share?
28 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and MiniMax-M3 has 41.