Model comparison
DeepSeek-V3.2-Speciale vs GLM-5.1
GLM-5.1 is the stronger model overall, scoring 47.8 to 39.7 on the Noometry Index. DeepSeek-V3.2-Speciale costs 2.5× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
DeepSeekSummary
- They share 3 benchmarks with published results for both. DeepSeek-V3.2-Speciale scores higher in 0 categories and GLM-5.1 in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.1 leads 66.9 to 46.0.
- The biggest single-benchmark swing is WeirdML: 46.7% for DeepSeek-V3.2-Speciale and 57.1% for GLM-5.1.
- DeepSeek-V3.2-Speciale is cheaper at $0.58 / $1.68 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
| DeepSeek-V3.2-Speciale | GLM-5.1 | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 39.7 | 47.8 |
| Released | 2025-12-01 | 2026-04-07 |
| Weights | Open | Open |
| Context window | 128K | 200K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.58 | $1.40 |
| Output $ / M tokens | $1.68 | $4.40 |
| Results tracked | 3 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
DeepSeek-V3.2-Speciale: 40.4 (#140), GLM-5.1: 48.7 (#55)
| Benchmark | DeepSeek-V3.2-Speciale | GLM-5.1 |
|---|---|---|
| WeirdML | 46.7% | 57.1% |
| SWE-bench Verified | — | 74.2% |
| LMArena WebDev | — | 1508 |
| SciCode | — | 43.8% |
| LMArena Coding | — | 1485 |
| ALE-Bench | — | 887.1 |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Speciale: —, GLM-5.1: 24.9 (#113)
| Benchmark | DeepSeek-V3.2-Speciale | GLM-5.1 |
|---|---|---|
| APEX-Agents | — | 40.9% |
| ExploitBench | — | 18.1% |
| GBAEval | — | 0% |
| Vending-Bench 2 | — | 5,634 |
Reasoning GLM-5.1 leads
DeepSeek-V3.2-Speciale: 32.9 (#73), GLM-5.1: 39.1 (#60)
| Benchmark | DeepSeek-V3.2-Speciale | GLM-5.1 |
|---|---|---|
| SimpleBench | 52.6% | 55.1% |
| NYT Connections (extended) | — | 77.7% |
| CritPt | — | 4.6% |
| Chess Puzzles | — | 19% |
| Thematic Generalization | — | 69.8% |
| LMArena Hard Prompts | — | 1472 |
| Epoch Capabilities Index | — | 149.84 |
Math Not comparable
DeepSeek-V3.2-Speciale: —, GLM-5.1: 49.7 (#60)
| Benchmark | DeepSeek-V3.2-Speciale | 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
DeepSeek-V3.2-Speciale: —, GLM-5.1: 54.9 (#50)
| Benchmark | DeepSeek-V3.2-Speciale | GLM-5.1 |
|---|---|---|
| GPQA Diamond | — | 89.9% |
| SimpleQA Verified | — | 34% |
| LMArena Expert | — | 1476 |
Multilingual Not comparable
DeepSeek-V3.2-Speciale: —, GLM-5.1: 55.0 (#36)
| Benchmark | DeepSeek-V3.2-Speciale | 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
DeepSeek-V3.2-Speciale: —, GLM-5.1: 76.3 (#42)
| Benchmark | DeepSeek-V3.2-Speciale | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | — | 1451 |
Long Context Not comparable
DeepSeek-V3.2-Speciale: —, GLM-5.1: 44.9 (#53)
| Benchmark | DeepSeek-V3.2-Speciale | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | — | 1466 |
Writing & Preference GLM-5.1 leads
DeepSeek-V3.2-Speciale: 46.0 (#222), GLM-5.1: 66.9 (#31)
| Benchmark | DeepSeek-V3.2-Speciale | GLM-5.1 |
|---|---|---|
| EQ-Bench Creative Writing | 1276 | 1592 |
| LMArena Text | — | 1461 |
| LMArena Creative Writing | — | 1453 |
| LMArena Multi-Turn | — | 1472 |
Frequently asked questions
Is DeepSeek-V3.2-Speciale better than GLM-5.1?
GLM-5.1 is the stronger model overall, scoring 47.8 to 39.7 on the Noometry Index. DeepSeek-V3.2-Speciale costs 2.5× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.2-Speciale or GLM-5.1?
DeepSeek-V3.2-Speciale is cheaper. It lists at $0.58 per million input tokens and $1.68 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is DeepSeek-V3.2-Speciale or GLM-5.1 better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 40.4 in the Noometry coding category.
Which has the bigger context window?
GLM-5.1 does, with 200K tokens against 128K.
How many benchmarks do DeepSeek-V3.2-Speciale and GLM-5.1 share?
3 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and GLM-5.1 has 41.