BlogLLM Benchmark Scores as Published, Side by Side
DeepSeek-V3.2-Exp: Benchmark Scores as Published
Every result the catalog holds for DeepSeek-V3.2-Exp: 26 tests in 7 areas, from 2 pages. 14 printed by DeepSeek itself, the rest by the company named beside each number. Each number is as printed; nothing is ranked or rescored.
Developer DeepSeekReleased 2025-09-29Input TextOutput TextWeights Open (MIT)Data version 2026103001, as of 2026-10-30
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| SWE-bench Verified | 67.8% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15; printed on 1 more page | Tools: enabled; exact tools in source |
| SWE-bench Multilingual | 57.9% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15; printed on 1 more page | Tools: enabled; exact tools in source |
| Terminal-Bench (version not stated) | 37.7% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15; printed on 1 more page | Tools: enabled; exact tools in source |
| Multi-SWE-bench | 30.6% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Harness: in-house harness derived from SWE-agent; Tools: enabled; bash and edit tools |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 79.9% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| AIME 2025 | 89.3% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| SciCode | 37.7% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
| HMMT February 2025 | 83.6% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| IMO-AnswerBench | 76% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 19.8% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| MMLU-Pro | 85% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| Humanity's Last Exam (with tools) | 20.3% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: enabled; search, code interpreter, web browsing; Context: 256000 |
| MMLU-Redux | 93.7% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
| SimpleQA | 97.1% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15 | Tools: enabled; exact tools in source |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LiveCodeBench v6 | 74.1% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
| Codeforces rating | 2121 | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15 | Tools: none |
| LiveCodeBench (version not stated) | 74.1% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15 | Tools: none |
| Aider polyglot | 74.5% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15 | Tools: none |
| OJBench (C++) | 38.2% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
Web Search and Research
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| BrowseComp | 40.1% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15; printed on 1 more page | Tools: enabled; exact tools in source |
| BrowseComp-ZH | 47.9% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15; printed on 1 more page | Tools: enabled; exact tools in source |
| Seal-0 | 38.5% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: enabled; search, code interpreter, web browsing; Context: 256000 |
| FRAMES | 80.2% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: enabled; search, code interpreter, web browsing; Context: 256000 |
| FinSearchComp T3 | 27% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: enabled; search, code interpreter, web browsing; Context: 256000 |
Writing and Conversation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Longform Writing | 72.5 | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
Healthcare
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| HealthBench | 46.9 | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
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-V3.1-Terminus
- DeepSeek-V3.1
- 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.