Model comparison
DeepSeek LLM 67B vs GLM-4.6
GLM-4.6 is the stronger model overall, scoring 41.4 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeekSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and GLM-4.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.6 leads 40.2 to 7.0.
Side by side
| DeepSeek LLM 67B | GLM-4.6 | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 24.9 | 41.4 |
| Released | 2023-11-29 | 2025-09-30 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 15 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
DeepSeek LLM 67B: 31.9 (#278), GLM-4.6: 40.1 (#148)
| Benchmark | DeepSeek LLM 67B | GLM-4.6 |
|---|---|---|
| LMArena Coding | 1096 | 1449 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1340 |
| SciCode | — | 38.4% |
| ALE-Bench | — | 340.82 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, GLM-4.6: 32.3 (#66)
| Benchmark | DeepSeek LLM 67B | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |
Reasoning GLM-4.6 leads
DeepSeek LLM 67B: 16.5 (#304), GLM-4.6: 23.7 (#172)
| Benchmark | DeepSeek LLM 67B | GLM-4.6 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1440 |
| Kagi LLM Benchmark | — | 47.4% |
| CritPt | — | 1.1% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math GLM-4.6 leads
DeepSeek LLM 67B: 8.7 (#324), GLM-4.6: 39.1 (#111)
| Benchmark | DeepSeek LLM 67B | GLM-4.6 |
|---|---|---|
| LMArena Math | 1108 | 1432 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-4.6 leads
DeepSeek LLM 67B: 7.0 (#313), GLM-4.6: 40.2 (#124)
| Benchmark | DeepSeek LLM 67B | GLM-4.6 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Vectara Hallucination Rate | — | 9.5% |
| LMArena Expert | — | 1431 |
Multilingual GLM-4.6 leads
DeepSeek LLM 67B: 29.4 (#267), GLM-4.6: 53.5 (#66)
| Benchmark | DeepSeek LLM 67B | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1073 | 1426 |
| LMArena Chinese | 1132 | 1499 |
| LMArena French | — | 1459 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1393 |
| LMArena Korean | — | 1400 |
| LMArena Russian | — | 1419 |
| LMArena Spanish | — | 1436 |
Instruction Following GLM-4.6 leads
DeepSeek LLM 67B: 55.4 (#277), GLM-4.6: 74.3 (#98)
| Benchmark | DeepSeek LLM 67B | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1410 |
Long Context GLM-4.6 leads
DeepSeek LLM 67B: 33.1 (#265), GLM-4.6: 43.4 (#94)
| Benchmark | DeepSeek LLM 67B | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1092 | 1422 |
Writing & Preference GLM-4.6 leads
DeepSeek LLM 67B: 31.6 (#282), GLM-4.6: 61.1 (#90)
| Benchmark | DeepSeek LLM 67B | GLM-4.6 |
|---|---|---|
| LMArena Text | 1105 | 1440 |
| LMArena Creative Writing | 1067 | 1411 |
| LMArena Multi-Turn | 1082 | 1427 |
| EQ-Bench Creative Writing | — | 1411 |
Frequently asked questions
Is DeepSeek LLM 67B better than GLM-4.6?
GLM-4.6 is the stronger model overall, scoring 41.4 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or GLM-4.6 better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and GLM-4.6 share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GLM-4.6 has 29.