BlogLLM Benchmark Scores as Published, Side by Side
DeepSeek-V3.1: Benchmark Scores as Published
Every result the catalog holds for DeepSeek-V3.1: 12 tests in 5 areas, from 1 page. All were printed by DeepSeek itself. Each number is as printed; nothing is ranked or rescored.
Developer DeepSeekReleased 2025-08-21Context window 128KInput TextOutput TextWeights Open (MIT)Data version 2026103001, as of 2026-10-30
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| SWE-bench Verified | 66% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: enabled; exact tools in source |
| SWE-bench Multilingual | 54.5% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: enabled; exact tools in source |
| Terminal-Bench (version not stated) | 31.3% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: enabled; exact tools in source |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 80.1% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: none |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 15.9% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: none |
| MMLU-Pro | 84.8% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: none |
| SimpleQA | 93.4% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: enabled; exact tools in source |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Codeforces rating | 2091 | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: none |
| LiveCodeBench (version not stated) | 74.8% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: none |
| Aider polyglot | 76.3% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: none |
Web Search and Research
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| BrowseComp | 30% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: enabled; exact tools in source |
| BrowseComp-ZH | 49.2% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: enabled; exact tools in source |
More from DeepSeek
- DeepSeek-V4.1-Flash-1017
- DeepSeek-V4.1-Flash
- DeepSeek-V4-Flash (Preview)
- DeepSeek-V4-Flash-Base
- DeepSeek-V4-Pro (Preview)
- DeepSeek-V4-Pro-Base
- DeepSeek-V3.2
- DeepSeek-V3.2-Base
- DeepSeek-V3.2-Speciale
- DeepSeek-V3.2-Exp
- DeepSeek-V3.1-Terminus
- DeepSeek-R1-0528
- DeepSeek-R1-0528-Qwen3-8B
- DeepSeek-V3-0324
- DeepSeek-R1
- DeepSeek-R1-Distill-Llama-70B
- DeepSeek-R1-Distill-Llama-8B
- DeepSeek-R1-Distill-Qwen-1.5B
- DeepSeek-R1-Distill-Qwen-14B
- DeepSeek-R1-Distill-Qwen-32B
- DeepSeek-R1-Distill-Qwen-7B
- DeepSeek-V3
- DeepSeek-V4-Flash-0731
- DeepSeek-V4-Pro-0813
- DeepSeek-V4-Vision-Exp
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.