Model comparison
Devstral Small 2505 vs GLM-5.3-Flash
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 1.6× less per token, which makes it the better buy when GLM-5.3-Flash's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Mistral AISummary
- They share 2 benchmarks with published results for both. Devstral Small 2505 scores higher in 0 categories and GLM-5.3-Flash in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.3-Flash leads 48.0 to 19.7.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 51.6% for GLM-5.3-Flash.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.15 / $0.50 for GLM-5.3-Flash.
- GLM-5.3-Flash accepts more context: 1M tokens versus 128K.
Side by side
| Devstral Small 2505 | GLM-5.3-Flash | |
|---|---|---|
| Provider | Mistral AI | Z.ai (Zhipu) |
| Noometry Index | 34.3 | 51.8 |
| Released | 2025-05-07 | 2026-08-20 |
| Weights | Open | Open |
| Context window | 128K | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.10 | $0.15 |
| Output $ / M tokens | $0.30 | $0.50 |
| Results tracked | 4 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
Devstral Small 2505: 38.9 (#166), GLM-5.3-Flash: 53.1 (#31)
| Benchmark | Devstral Small 2505 | GLM-5.3-Flash |
|---|---|---|
| SciCode | 28.8% | 51.6% |
| DeepSWE | — | 63.4% |
| FrontierCode | — | 31.8% |
| SWE-bench Verified (bash only) | 56.4% | — |
| CursorBench | — | 36.8% |
| LMArena WebDev | — | 1609 |
| FrontierSWE | — | 18.1% |
| LMArena Coding | — | 1508 |
| ALE-Bench | — | 303.55 |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, GLM-5.3-Flash: 34.2 (#47)
| Benchmark | Devstral Small 2505 | GLM-5.3-Flash |
|---|---|---|
| APEX-Agents | — | 52.8% |
| GDP.pdf | — | 14% |
Reasoning GLM-5.3-Flash leads
Devstral Small 2505: 19.7 (#252), GLM-5.3-Flash: 48.0 (#42)
| Benchmark | Devstral Small 2505 | GLM-5.3-Flash |
|---|---|---|
| CritPt | 0% | 15.4% |
| ARC-AGI-2 | — | 65.8% |
| Kagi LLM Benchmark | 37.7% | — |
| ARC-AGI-1 | — | 91% |
| Chess Puzzles | — | 14% |
| LMArena Hard Prompts | — | 1491 |
| Mystery Game Puzzles | — | 8% |
| Surface Evolver Bench | — | 52.5% |
| Bench to the Future 3 | — | 0.15 |
| Epoch Capabilities Index | — | 151.88 |
Math Not comparable
Devstral Small 2505: —, GLM-5.3-Flash: 53.3 (#47)
| Benchmark | Devstral Small 2505 | GLM-5.3-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 55.8% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 93.9% |
| ProofBench | — | 21% |
| LMArena Math | — | 1500 |
Knowledge Not comparable
Devstral Small 2505: —, GLM-5.3-Flash: 58.4 (#36)
| Benchmark | Devstral Small 2505 | GLM-5.3-Flash |
|---|---|---|
| GPQA Diamond | — | 90.2% |
| LMArena Expert | — | 1513 |
Multimodal Not comparable
Devstral Small 2505: —, GLM-5.3-Flash: 42.8 (#27)
| Benchmark | Devstral Small 2505 | GLM-5.3-Flash |
|---|---|---|
| LMArena Vision | — | 1296 |
Multilingual Not comparable
Devstral Small 2505: —, GLM-5.3-Flash: 56.0 (#25)
| Benchmark | Devstral Small 2505 | GLM-5.3-Flash |
|---|---|---|
| LMArena Non-English | — | 1462 |
| LMArena Chinese | — | 1527 |
| LMArena French | — | 1496 |
| LMArena German | — | 1470 |
| LMArena Japanese | — | 1429 |
| LMArena Korean | — | 1446 |
| LMArena Russian | — | 1469 |
| LMArena Spanish | — | 1471 |
Instruction Following Not comparable
Devstral Small 2505: —, GLM-5.3-Flash: 77.5 (#20)
| Benchmark | Devstral Small 2505 | GLM-5.3-Flash |
|---|---|---|
| LMArena Instruction Following | — | 1478 |
Long Context Not comparable
Devstral Small 2505: —, GLM-5.3-Flash: 45.4 (#39)
| Benchmark | Devstral Small 2505 | GLM-5.3-Flash |
|---|---|---|
| LMArena Longer Query | — | 1482 |
Writing & Preference Not comparable
Devstral Small 2505: —, GLM-5.3-Flash: 65.3 (#50)
| Benchmark | Devstral Small 2505 | GLM-5.3-Flash |
|---|---|---|
| LMArena Text | — | 1471 |
| LMArena Creative Writing | — | 1442 |
| LMArena Multi-Turn | — | 1467 |
Frequently asked questions
Is Devstral Small 2505 better than GLM-5.3-Flash?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 1.6× less per token, which makes it the better buy when GLM-5.3-Flash's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or GLM-5.3-Flash?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; GLM-5.3-Flash lists at $0.15 and $0.50.
Is Devstral Small 2505 or GLM-5.3-Flash better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 128K.
How many benchmarks do Devstral Small 2505 and GLM-5.3-Flash share?
2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and GLM-5.3-Flash has 40.