Model comparison
DeepSeek LLM 67B vs GLM-4.7
GLM-4.7 is the stronger model overall, scoring 41.7 to 24.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeekSummary
- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and GLM-4.7 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 7.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 83.3% for GLM-4.7.
Side by side
| DeepSeek LLM 67B | GLM-4.7 | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 24.8 | 41.7 |
| Released | 2023-11-29 | 2025-12-22 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 15 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
DeepSeek LLM 67B: 31.3 (#273), GLM-4.7: 43.6 (#74)
| Benchmark | DeepSeek LLM 67B | GLM-4.7 |
|---|---|---|
| LMArena Coding | 1096 | 1454 |
| LMArena WebDev | — | 1435 |
| SciCode | — | 45.1% |
| ALE-Bench | — | 399.48 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, GLM-4.7: 26.4 (#96)
| Benchmark | DeepSeek LLM 67B | GLM-4.7 |
|---|---|---|
| Terminal-Bench | — | 33.4% |
| Vending-Bench 2 | — | 2,377 |
Reasoning GLM-4.7 leads
DeepSeek LLM 67B: 15.9 (#300), GLM-4.7: 23.7 (#161)
| Benchmark | DeepSeek LLM 67B | GLM-4.7 |
|---|---|---|
| Chess Puzzles | 0% | 6% |
| LMArena Hard Prompts | 1070 | 1443 |
| Epoch Capabilities Index | 110.54 | 143.53 |
| SimpleBench | — | 47.7% |
| CritPt | — | 1.7% |
Math GLM-4.7 leads
DeepSeek LLM 67B: 8.1 (#318), GLM-4.7: 37.7 (#92)
| Benchmark | DeepSeek LLM 67B | GLM-4.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 83.3% |
| LMArena Math | 1108 | 1423 |
| ProofBench | — | 6% |
| MATH Level 5 | 6.4% | — |
| FrontierMath (Feb 2025 set) | — | 2.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge GLM-4.7 leads
DeepSeek LLM 67B: 7.1 (#308), GLM-4.7: 47.0 (#74)
| Benchmark | DeepSeek LLM 67B | GLM-4.7 |
|---|---|---|
| GPQA Diamond | 24.6% | 83.3% |
| SimpleQA Verified | — | 32.2% |
| Vectara Hallucination Rate | — | 11.7% |
| LMArena Expert | — | 1424 |
Multilingual GLM-4.7 leads
DeepSeek LLM 67B: 29.5 (#262), GLM-4.7: 53.0 (#75)
| Benchmark | DeepSeek LLM 67B | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 1073 | 1417 |
| LMArena Chinese | 1132 | 1495 |
| LMArena French | — | 1432 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1439 |
| LMArena Korean | — | 1401 |
| LMArena Russian | — | 1423 |
| LMArena Spanish | — | 1433 |
Instruction Following GLM-4.7 leads
DeepSeek LLM 67B: 55.7 (#272), GLM-4.7: 74.6 (#90)
| Benchmark | DeepSeek LLM 67B | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1411 |
Long Context GLM-4.7 leads
DeepSeek LLM 67B: 33.1 (#260), GLM-4.7: 42.8 (#111)
| Benchmark | DeepSeek LLM 67B | GLM-4.7 |
|---|---|---|
| LMArena Longer Query | 1092 | 1432 |
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |
Writing & Preference GLM-4.7 leads
DeepSeek LLM 67B: 31.8 (#277), GLM-4.7: 61.1 (#89)
| Benchmark | DeepSeek LLM 67B | GLM-4.7 |
|---|---|---|
| LMArena Text | 1105 | 1436 |
| LMArena Creative Writing | 1067 | 1401 |
| LMArena Multi-Turn | 1082 | 1446 |
| EQ-Bench Creative Writing | — | 1413 |
Frequently asked questions
Is DeepSeek LLM 67B better than GLM-4.7?
GLM-4.7 is the stronger model overall, scoring 41.7 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or GLM-4.7 better for coding?
GLM-4.7 scores higher on coding benchmarks: 43.6 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and GLM-4.7 share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GLM-4.7 has 36.