Model comparison
DeepSeek-V3.2-Exp vs GLM-4.6
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 40.9 on the Noometry Index.
Last verified . 28 shared benchmarks.
DeepSeekSummary
- They share 28 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 7 categories and GLM-4.6 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.6 to 39.6.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 56.7% for DeepSeek-V3.2-Exp and 72.4% for GLM-4.6.
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- GLM-4.6 accepts more context: 205K tokens versus 164K.
Side by side
| DeepSeek-V3.2-Exp | GLM-4.6 | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 44.9 | 40.9 |
| Released | 2025-09-29 | 2025-09-30 |
| Weights | Open | Open |
| Context window | 164K | 205K |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.26 | $0.60 |
| Output $ / M tokens | $0.38 | $2.20 |
| Results tracked | 48 | 29 |
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-4.6: 39.9 (#137)
| Benchmark | DeepSeek-V3.2-Exp | GLM-4.6 |
|---|---|---|
| SWE-bench Verified (bash only) | 70% | 55.4% |
| LMArena WebDev | 1362 | 1339 |
| SciCode | 38.9% | 38.4% |
| LMArena Coding | 1454 | 1449 |
| Aider Polyglot | 74.2% | — |
| SWE-bench Multilingual | 59% | — |
| WeirdML | 39.5% | — |
| ALE-Bench | — | 340.82 |
Agentic & Tool Use DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 37.9 (#31), GLM-4.6: 32.1 (#60)
| Benchmark | DeepSeek-V3.2-Exp | GLM-4.6 |
|---|---|---|
| Terminal-Bench | 39.6% | 24.5% |
| Berkeley Function Calling Leaderboard | 56.7% | 72.4% |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning GLM-4.6 leads
DeepSeek-V3.2-Exp: 22.0 (#185), GLM-4.6: 23.1 (#168)
| Benchmark | DeepSeek-V3.2-Exp | GLM-4.6 |
|---|---|---|
| Kagi LLM Benchmark | 52.2% | 47.4% |
| CritPt | 2.9% | 1.1% |
| LMArena Hard Prompts | 1433 | 1440 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| 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-4.6: 36.4 (#115)
| Benchmark | DeepSeek-V3.2-Exp | GLM-4.6 |
|---|---|---|
| LMArena Math | 1435 | 1431 |
| FrontierMath (Feb 2025 set) | 22.1% | 3.8% |
| FrontierMath Tier 4 (v1) | 2.1% | 2.1% |
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 8% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.6 (#61), GLM-4.6: 39.6 (#118)
| Benchmark | DeepSeek-V3.2-Exp | GLM-4.6 |
|---|---|---|
| Vectara Hallucination Rate | 5.3% | 9.5% |
| LMArena Expert | 1436 | 1432 |
| GPQA Diamond | 83.4% | — |
Multilingual GLM-4.6 leads
DeepSeek-V3.2-Exp: 52.4 (#85), GLM-4.6: 53.6 (#62)
| Benchmark | DeepSeek-V3.2-Exp | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1409 | 1426 |
| LMArena Chinese | 1461 | 1500 |
| LMArena French | 1435 | 1459 |
| LMArena German | 1440 | 1447 |
| LMArena Japanese | 1377 | 1394 |
| LMArena Korean | 1372 | 1401 |
| LMArena Russian | 1423 | 1418 |
| LMArena Spanish | 1441 | 1436 |
Instruction Following Too close to call
DeepSeek-V3.2-Exp: 74.7 (#89), GLM-4.6: 74.5 (#93)
| Benchmark | DeepSeek-V3.2-Exp | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1413 | 1410 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#15), GLM-4.6: 43.4 (#91)
| Benchmark | DeepSeek-V3.2-Exp | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1428 | 1423 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.5 (#73), GLM-4.6: 61.3 (#86)
| Benchmark | DeepSeek-V3.2-Exp | GLM-4.6 |
|---|---|---|
| LMArena Text | 1425 | 1440 |
| LMArena Creative Writing | 1403 | 1411 |
| EQ-Bench Creative Writing | 1515 | 1411 |
| LMArena Multi-Turn | 1427 | 1427 |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than GLM-4.6?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 40.9 on the Noometry Index.
Which is cheaper, DeepSeek-V3.2-Exp or GLM-4.6?
DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is DeepSeek-V3.2-Exp or GLM-4.6 better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.4 versus 39.9 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 164K.
How many benchmarks do DeepSeek-V3.2-Exp and GLM-4.6 share?
28 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 48 scored results on Noometry and GLM-4.6 has 29.