Model comparison
DeepSeek-V3.2-Exp vs GLM-5V-Turbo
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 43.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 4 categories and GLM-5V-Turbo in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.6 to 39.9.
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $1.20 / $4 for GLM-5V-Turbo.
- GLM-5V-Turbo accepts more context: 200K tokens versus 164K.
- DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Exp | GLM-5V-Turbo | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 44.9 | 43.1 |
| Released | 2025-09-29 | 2026-04-01 |
| Weights | Open | Proprietary |
| Context window | 164K | 200K |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.26 | $1.20 |
| Output $ / M tokens | $0.38 | $4 |
| Results tracked | 48 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 46.4 (#61), GLM-5V-Turbo: 41.8 (#105)
| Benchmark | DeepSeek-V3.2-Exp | GLM-5V-Turbo |
|---|---|---|
| LMArena WebDev | 1362 | 1400 |
| LMArena Coding | 1454 | 1467 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| WeirdML | 39.5% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Exp: 37.9 (#31), GLM-5V-Turbo: —
| Benchmark | DeepSeek-V3.2-Exp | GLM-5V-Turbo |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning GLM-5V-Turbo leads
DeepSeek-V3.2-Exp: 22.0 (#185), GLM-5V-Turbo: 28.5 (#87)
| Benchmark | DeepSeek-V3.2-Exp | GLM-5V-Turbo |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1443 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
| Epoch Capabilities Index | 146.28 | — |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 40.8 (#75), GLM-5V-Turbo: 36.6 (#109)
| Benchmark | DeepSeek-V3.2-Exp | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | 1435 | 1440 |
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 8% | — |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.6 (#61), GLM-5V-Turbo: 39.9 (#113)
| Benchmark | DeepSeek-V3.2-Exp | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | 1436 | 1451 |
| GPQA Diamond | 83.4% | — |
| Vectara Hallucination Rate | 5.3% | — |
Multimodal Not comparable
DeepSeek-V3.2-Exp: —, GLM-5V-Turbo: 40.1 (#41)
| Benchmark | DeepSeek-V3.2-Exp | GLM-5V-Turbo |
|---|---|---|
| LMArena Vision | — | 1264 |
| LMArena Document | — | 1416 |
Multilingual Too close to call
DeepSeek-V3.2-Exp: 52.4 (#85), GLM-5V-Turbo: 53.2 (#69)
| Benchmark | DeepSeek-V3.2-Exp | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | 1409 | 1420 |
| LMArena Chinese | 1461 | 1488 |
| LMArena French | 1435 | 1443 |
| LMArena German | 1440 | 1422 |
| LMArena Korean | 1372 | 1399 |
| LMArena Russian | 1423 | 1432 |
| LMArena Spanish | 1441 | 1446 |
| LMArena Japanese | 1377 | — |
Instruction Following Too close to call
DeepSeek-V3.2-Exp: 74.7 (#89), GLM-5V-Turbo: 75.1 (#75)
| Benchmark | DeepSeek-V3.2-Exp | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | 1413 | 1422 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#15), GLM-5V-Turbo: 44.0 (#76)
| Benchmark | DeepSeek-V3.2-Exp | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | 1428 | 1439 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference Too close to call
DeepSeek-V3.2-Exp: 62.5 (#73), GLM-5V-Turbo: 62.6 (#69)
| Benchmark | DeepSeek-V3.2-Exp | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | 1425 | 1437 |
| LMArena Creative Writing | 1403 | 1414 |
| LMArena Multi-Turn | 1427 | 1432 |
| EQ-Bench Creative Writing | 1515 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than GLM-5V-Turbo?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 43.1 on the Noometry Index.
Which is cheaper, DeepSeek-V3.2-Exp or GLM-5V-Turbo?
DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; GLM-5V-Turbo lists at $1.20 and $4.
Is DeepSeek-V3.2-Exp or GLM-5V-Turbo better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.4 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
GLM-5V-Turbo does, with 200K tokens against 164K.
How many benchmarks do DeepSeek-V3.2-Exp and GLM-5V-Turbo share?
17 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 48 scored results on Noometry and GLM-5V-Turbo has 19.