DeepSeek-V4-ProvsGLM 5.1
Across 7 shared benchmarks, GLM 5.1 leads overall: DeepSeek-V4-Pro wins 2, GLM 5.1 wins 5, with 0 ties and an average score difference of -15.66.
DeepSeek-V4-Pro
DeepSeek-AI · 2026-04-24 · Reasoning model
GLM 5.1
智谱AI · 2026-03-27 · Reasoning model
DeepSeek-V4-Pro2 wins(29%)(71%)5 winsGLM 5.1
Benchmark scores
Grouped by capability, sorted by largest gap within each. 7 shared benchmarks.
General Knowledge
GLM 5.1 2/3| Benchmark | DeepSeek-V4-Pro | GLM 5.1 | Diff |
|---|---|---|---|
| HLE | 7.70156 / 172Normal (No Tools) | 52.3019 / 172Thinking (With Tools) | -44.60 |
| GPQA Diamond | 72.90108 / 187Normal (No Tools) | 86.2047 / 187Thinking (No Tools) | -13.30 |
| LiveBench | 73.5823 / 115Normal (No Tools) | 70.1837 / 115Normal (No Tools) | +3.40 |
AI Agent - Information Search
DeepSeek-V4-Pro 1/1| Benchmark | DeepSeek-V4-Pro | GLM 5.1 | Diff |
|---|---|---|---|
| BrowseComp | 83.4013 / 53极高强度思考（工具） | 79.3017 / 53Thinking (With Tools + Internet) | +4.10 |
AI Agent - Tool Usage
GLM 5.1 1/1| Benchmark | DeepSeek-V4-Pro | GLM 5.1 | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 59.1022 / 47Normal (With Tools) | 63.5013 / 47Thinking (With Tools) | -4.40 |
Coding and Software Engineer
GLM 5.1 1/1| Benchmark | DeepSeek-V4-Pro | GLM 5.1 | Diff |
|---|---|---|---|
| SWE-Bench Pro - Public | 52.1038 / 54Normal (With Tools) | 58.4015 / 54Thinking (With Tools) | -6.30 |
Math and Reasoning
GLM 5.1 1/1| Benchmark | DeepSeek-V4-Pro | GLM 5.1 | Diff |
|---|---|---|---|
| IMO-AnswerBench | 35.3021 / 21Normal (No Tools) | 83.8012 / 21Thinking (No Tools) | -48.50 |
Specs
| Field | DeepSeek-V4-Pro | GLM 5.1 |
|---|---|---|
| Publisher | DeepSeek-AI | 智谱AI |
| Release date | 2026-04-24 | 2026-03-27 |
| Model type | Reasoning model | Reasoning model |
| Architecture | MoE | MoE |
| Parameters | 1.6T | 75.4B |
| Context length | 1M | 200K |
| Max output | 375K | 125K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | DeepSeek-V4-Pro | GLM 5.1 |
|---|---|---|
| Text input | $0.435 / 1M tokens | $1.4 / 1M tokens |
| Text output | $0.87 / 1M tokens | $4.4 / 1M tokens |
| Cache read | $0.87 / 1M tokens | $4.4 / 1M tokens |
| Cache write | $0.003625 / 1M tokens | $0.26 / 1M tokens |
Summary
- DeepSeek-V4-Proleads in:AI Agent - Information Search (1/1)
- GLM 5.1leads in:General Knowledge (2/3), AI Agent - Tool Usage (1/1), Coding and Software Engineer (1/1), Math and Reasoning (1/1)
On average across the 7 shared benchmarks, GLM 5.1 scores 15.66 higher.
Largest single-benchmark gap: IMO-AnswerBench — DeepSeek-V4-Pro 35.30 vs GLM 5.1 83.80 (-48.50).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.