Model comparison
Devstral Small 2505 vs GLM-5V-Turbo
GLM-5V-Turbo is the stronger model overall, scoring 43.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 13× less per token, which makes it the better buy when GLM-5V-Turbo's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in reasoning, where GLM-5V-Turbo leads 29.7 to 19.7.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.20 / $4 for GLM-5V-Turbo.
- GLM-5V-Turbo accepts more context: 200K tokens versus 128K.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | GLM-5V-Turbo | |
|---|---|---|
| Provider | Mistral AI | Z.ai (Zhipu) |
| Noometry Index | 34.3 | 43.8 |
| Released | 2025-05-07 | 2026-04-01 |
| Weights | Open | Proprietary |
| Context window | 128K | 200K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.10 | $1.20 |
| Output $ / M tokens | $0.30 | $4 |
| Results tracked | 4 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5V-Turbo leads
Devstral Small 2505: 38.9 (#166), GLM-5V-Turbo: 42.1 (#111)
| Benchmark | Devstral Small 2505 | GLM-5V-Turbo |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1401 |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1466 |
Reasoning GLM-5V-Turbo leads
Devstral Small 2505: 19.7 (#252), GLM-5V-Turbo: 29.7 (#89)
| Benchmark | Devstral Small 2505 | GLM-5V-Turbo |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1443 |
Math Not comparable
Devstral Small 2505: —, GLM-5V-Turbo: 39.4 (#106)
| Benchmark | Devstral Small 2505 | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | — | 1441 |
Knowledge Not comparable
Devstral Small 2505: —, GLM-5V-Turbo: 40.6 (#117)
| Benchmark | Devstral Small 2505 | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | — | 1452 |
Multimodal Not comparable
Devstral Small 2505: —, GLM-5V-Turbo: 40.9 (#42)
| Benchmark | Devstral Small 2505 | GLM-5V-Turbo |
|---|---|---|
| LMArena Vision | — | 1264 |
| LMArena Document | — | 1416 |
Multilingual Not comparable
Devstral Small 2505: —, GLM-5V-Turbo: 53.0 (#73)
| Benchmark | Devstral Small 2505 | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | — | 1420 |
| LMArena Chinese | — | 1488 |
| LMArena French | — | 1444 |
| LMArena German | — | 1423 |
| LMArena Korean | — | 1396 |
| LMArena Russian | — | 1431 |
| LMArena Spanish | — | 1450 |
Instruction Following Not comparable
Devstral Small 2505: —, GLM-5V-Turbo: 75.0 (#80)
| Benchmark | Devstral Small 2505 | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | — | 1423 |
Long Context Not comparable
Devstral Small 2505: —, GLM-5V-Turbo: 44.0 (#80)
| Benchmark | Devstral Small 2505 | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | — | 1438 |
Writing & Preference Not comparable
Devstral Small 2505: —, GLM-5V-Turbo: 62.5 (#73)
| Benchmark | Devstral Small 2505 | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | — | 1437 |
| LMArena Creative Writing | — | 1416 |
| LMArena Multi-Turn | — | 1432 |
Frequently asked questions
Is Devstral Small 2505 better than GLM-5V-Turbo?
GLM-5V-Turbo is the stronger model overall, scoring 43.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 13× less per token, which makes it the better buy when GLM-5V-Turbo's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or GLM-5V-Turbo?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; GLM-5V-Turbo lists at $1.20 and $4.
Is Devstral Small 2505 or GLM-5V-Turbo better for coding?
GLM-5V-Turbo scores higher on coding benchmarks: 42.1 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
GLM-5V-Turbo does, with 200K tokens against 128K.
How many benchmarks do Devstral Small 2505 and GLM-5V-Turbo share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and GLM-5V-Turbo has 19.