Model comparison
Devstral Small 2505 vs GLM-5.1
GLM-5.1 is the stronger model overall, scoring 47.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 14× less per token, which makes it the better buy when GLM-5.1'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-5.1 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 19.7.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 43.8% for GLM-5.1.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 128K.
Side by side
| Devstral Small 2505 | GLM-5.1 | |
|---|---|---|
| Provider | Mistral AI | Z.ai (Zhipu) |
| Noometry Index | 34.3 | 47.8 |
| Released | 2025-05-07 | 2026-04-07 |
| Weights | Open | Open |
| Context window | 128K | 200K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.10 | $1.40 |
| Output $ / M tokens | $0.30 | $4.40 |
| Results tracked | 4 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
Devstral Small 2505: 38.9 (#166), GLM-5.1: 48.7 (#55)
| Benchmark | Devstral Small 2505 | GLM-5.1 |
|---|---|---|
| SciCode | 28.8% | 43.8% |
| SWE-bench Verified | — | 74.2% |
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1508 |
| WeirdML | — | 57.1% |
| LMArena Coding | — | 1485 |
| ALE-Bench | — | 887.1 |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, GLM-5.1: 24.9 (#113)
| Benchmark | Devstral Small 2505 | GLM-5.1 |
|---|---|---|
| APEX-Agents | — | 40.9% |
| ExploitBench | — | 18.1% |
| GBAEval | — | 0% |
| Vending-Bench 2 | — | 5,634 |
Reasoning GLM-5.1 leads
Devstral Small 2505: 19.7 (#252), GLM-5.1: 39.1 (#60)
| Benchmark | Devstral Small 2505 | GLM-5.1 |
|---|---|---|
| CritPt | 0% | 4.6% |
| SimpleBench | — | 55.1% |
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 77.7% |
| Chess Puzzles | — | 19% |
| Thematic Generalization | — | 69.8% |
| LMArena Hard Prompts | — | 1472 |
| Epoch Capabilities Index | — | 149.84 |
Math Not comparable
Devstral Small 2505: —, GLM-5.1: 49.7 (#60)
| Benchmark | Devstral Small 2505 | GLM-5.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 36.8% |
| MathArena Final-Answer Competitions | — | 67.1% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | — | 22.2% |
| LMArena Math | — | 1473 |
| FrontierMath (Feb 2025 set) | — | 33.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge Not comparable
Devstral Small 2505: —, GLM-5.1: 54.9 (#50)
| Benchmark | Devstral Small 2505 | GLM-5.1 |
|---|---|---|
| GPQA Diamond | — | 89.9% |
| SimpleQA Verified | — | 34% |
| LMArena Expert | — | 1476 |
Multilingual Not comparable
Devstral Small 2505: —, GLM-5.1: 55.0 (#36)
| Benchmark | Devstral Small 2505 | GLM-5.1 |
|---|---|---|
| LMArena Non-English | — | 1447 |
| LMArena Chinese | — | 1515 |
| LMArena French | — | 1474 |
| LMArena German | — | 1465 |
| LMArena Japanese | — | 1434 |
| LMArena Korean | — | 1418 |
| LMArena Russian | — | 1454 |
| LMArena Spanish | — | 1469 |
Instruction Following Not comparable
Devstral Small 2505: —, GLM-5.1: 76.3 (#42)
| Benchmark | Devstral Small 2505 | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | — | 1451 |
Long Context Not comparable
Devstral Small 2505: —, GLM-5.1: 44.9 (#53)
| Benchmark | Devstral Small 2505 | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | — | 1466 |
Writing & Preference Not comparable
Devstral Small 2505: —, GLM-5.1: 66.9 (#31)
| Benchmark | Devstral Small 2505 | GLM-5.1 |
|---|---|---|
| LMArena Text | — | 1461 |
| LMArena Creative Writing | — | 1453 |
| EQ-Bench Creative Writing | — | 1592 |
| LMArena Multi-Turn | — | 1472 |
Frequently asked questions
Is Devstral Small 2505 better than GLM-5.1?
GLM-5.1 is the stronger model overall, scoring 47.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 14× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or GLM-5.1?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is Devstral Small 2505 or GLM-5.1 better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
GLM-5.1 does, with 200K tokens against 128K.
How many benchmarks do Devstral Small 2505 and GLM-5.1 share?
2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and GLM-5.1 has 41.