DeepSeek V3.2 vs GLM 5.1
Head to head on 24 shared benchmarks, with price, context window, and release dates.
Benchmark scores
44evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GLM 5.1 Zai | 64.5% | 40.0% | 1589elo | 73.5 | 33.5% | 83.9% | 27.9% | 52.0% | 72.7% | 75.4% | 63.2% | 68.5% | 71.8% | 84.9% | 72.5% | 67.0% | 85.4% | 22.2% | 36.1% | 71.2% | 35.6% | 69.8 | 31.5% | 97.1% | - | - | - | 20.8% | 35.9% | 1.13 | - | 44.8% | 34.7% | 15.1% | - | - | - | 41.6% | 72.3% | 34.6% | 5.24 | - | - | 52.5% | 53.6% |
| DeepSeek V3.2 DeepSeek | 47.9% | 16.0% | 1511elo | 66.8 | 22.1% | 75.1% | 11.2% | 49.0% | 65.9% | 64.6% | 50.0% | 48.2% | 70.4% | 85.0% | 77.2% | 57.5% | 83.7% | 8.0% | 38.7% | 68.2% | 32.6% | 65 | 5.1% | 78.9% | 74.7% | 74.2% | 59.0% | - | - | - | 0.0% | - | - | - | 31.3% | 68.0% | 59.3% | - | - | - | - | 59.0% | 70.0% | - | 51.7% |
2 / 2 models
| Attribute | DeepSeek V3.2 DeepSeek | GLM 5.1 Zai |
|---|---|---|
| Description | DeepSeek V3.2 is an AI model from DeepSeek, released with open weights. | GLM-5.1 is an AI model from Zai, released with open weights. |
| Family | Deepseek | Glm |
| Params | - | - |
| Open weights | open | open |
| License | mit | mit |
| Released | 1 Dec 2025 | 7 Apr 2026 |
| Context | 163,840 | 204,800 |
| Input $/1M | $0.28 | $1.39 |
| Output $/1M | $0.42 | $4.40 |
| Cache read $/1M | $0.130 | $0.234 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text | text |
| Providers | - | - |
| Publisher | DeepSeek | Zai |
| Reported scores | Aider Polyglot Benchmark74.2% (Aider) MathArena57.47% GPQA Diamond75.1% (AA) Humanity's Last Exam (HLE)11.2% (AA) | IFBench52.0% (AA) τ²-bench (Tau²-bench)97.1% (AA) Terminal-Bench (Hard)35.6% (AA) Vals Index52.5% Vibe Code Bench v1.131.5% |
FAQ
- Is DeepSeek V3.2 or GLM 5.1 better?
- Across the 24 benchmarks both models report on Sophon, GLM 5.1 leads on 21 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do DeepSeek V3.2 and GLM 5.1 compare on GPQA Diamond?
- DeepSeek V3.2 scores 75.1% and GLM 5.1 scores 83.9% on GPQA Diamond.
- Which is cheaper, DeepSeek V3.2 or GLM 5.1?
- DeepSeek V3.2 is cheaper at $0.42 per million output tokens against $4.40 for GLM 5.1 - about 10.5x.
- When were DeepSeek V3.2 and GLM 5.1 released?
- DeepSeek V3.2 was released 1 Dec 2025 by DeepSeek. GLM 5.1 was released 7 Apr 2026 by Zai.
Comparing something else? Build your own side-by-side.