Model comparison
GLM-5V-Turbo vs MiniMax-M2.5
GLM-5V-Turbo is the stronger model overall, scoring 43.8 to 38.3 on the Noometry Index. MiniMax-M2.5 costs 3.6× less per token, which makes it the better buy when GLM-5V-Turbo's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
MiniMaxSummary
- They share 17 benchmarks with published results for both. GLM-5V-Turbo scores higher in 7 categories and MiniMax-M2.5 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5V-Turbo leads 39.4 to 26.9.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.20 / $4 for GLM-5V-Turbo.
- MiniMax-M2.5 accepts more context: 205K tokens versus 200K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| GLM-5V-Turbo | MiniMax-M2.5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | MiniMax |
| Noometry Index | 43.8 | 38.3 |
| Released | 2026-04-01 | 2026-02-12 |
| Weights | Proprietary | Open |
| Context window | 200K | 205K |
| Max output | 131K | 131K |
| Input $ / M tokens | $1.20 | $0.30 |
| Output $ / M tokens | $4 | $1.20 |
| Results tracked | 19 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
GLM-5V-Turbo: 42.1 (#111), MiniMax-M2.5: 48.1 (#58)
| Benchmark | GLM-5V-Turbo | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1401 | 1387 |
| LMArena Coding | 1466 | 1381 |
| SWE-bench Verified (bash only) | — | 75.8% |
| SWE-bench Multilingual | — | 68.3% |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use Not comparable
GLM-5V-Turbo: —, MiniMax-M2.5: 30.4 (#77)
| Benchmark | GLM-5V-Turbo | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |
Reasoning GLM-5V-Turbo leads
GLM-5V-Turbo: 29.7 (#89), MiniMax-M2.5: 17.5 (#292)
| Benchmark | GLM-5V-Turbo | MiniMax-M2.5 |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1372 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| Epoch Capabilities Index | — | 146.68 |
Math GLM-5V-Turbo leads
GLM-5V-Turbo: 39.4 (#106), MiniMax-M2.5: 26.9 (#253)
| Benchmark | GLM-5V-Turbo | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1441 | 1378 |
| ProofBench | — | 4% |
Knowledge GLM-5V-Turbo leads
GLM-5V-Turbo: 40.6 (#117), MiniMax-M2.5: 39.2 (#135)
| Benchmark | GLM-5V-Turbo | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1452 | 1379 |
| Vectara Hallucination Rate | — | 9.1% |
Multimodal Not comparable
GLM-5V-Turbo: 40.9 (#42), MiniMax-M2.5: —
| Benchmark | GLM-5V-Turbo | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 1264 | — |
| LMArena Document | 1416 | — |
Multilingual GLM-5V-Turbo leads
GLM-5V-Turbo: 53.0 (#73), MiniMax-M2.5: 47.1 (#152)
| Benchmark | GLM-5V-Turbo | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1420 | 1338 |
| LMArena Chinese | 1488 | 1393 |
| LMArena French | 1444 | 1362 |
| LMArena German | 1423 | 1362 |
| LMArena Korean | 1396 | 1232 |
| LMArena Russian | 1431 | 1358 |
| LMArena Spanish | 1450 | 1354 |
| LMArena Japanese | — | 1171 |
Instruction Following GLM-5V-Turbo leads
GLM-5V-Turbo: 75.0 (#80), MiniMax-M2.5: 71.5 (#148)
| Benchmark | GLM-5V-Turbo | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1423 | 1353 |
Long Context GLM-5V-Turbo leads
GLM-5V-Turbo: 44.0 (#80), MiniMax-M2.5: 37.5 (#216)
| Benchmark | GLM-5V-Turbo | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1438 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference GLM-5V-Turbo leads
GLM-5V-Turbo: 62.5 (#73), MiniMax-M2.5: 53.9 (#153)
| Benchmark | GLM-5V-Turbo | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1437 | 1359 |
| LMArena Creative Writing | 1416 | 1331 |
| LMArena Multi-Turn | 1432 | 1364 |
| EQ-Bench Creative Writing | — | 1361 |
Frequently asked questions
Is GLM-5V-Turbo better than MiniMax-M2.5?
GLM-5V-Turbo is the stronger model overall, scoring 43.8 to 38.3 on the Noometry Index. MiniMax-M2.5 costs 3.6× less per token, which makes it the better buy when GLM-5V-Turbo's lead doesn't matter for your workload.
Which is cheaper, GLM-5V-Turbo or MiniMax-M2.5?
MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GLM-5V-Turbo lists at $1.20 and $4.
Is GLM-5V-Turbo or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 42.1 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.5 does, with 205K tokens against 200K.
How many benchmarks do GLM-5V-Turbo and MiniMax-M2.5 share?
17 benchmarks have published results for both models. GLM-5V-Turbo has 19 scored results on Noometry and MiniMax-M2.5 has 33.