Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
DeepSeek V3.2 (Thinking)
67
Winner · 4/8 categoriesGemma 4 E2B
~39
0/8 categoriesDeepSeek V3.2 (Thinking)· Gemma 4 E2B
Pick DeepSeek V3.2 (Thinking) if you want the stronger benchmark profile. Gemma 4 E2B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
DeepSeek V3.2 (Thinking) is clearly ahead on the aggregate, 67 to 39. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
DeepSeek V3.2 (Thinking)'s sharpest advantage is in reasoning, where it averages 60.1 against 19.1. The single biggest benchmark swing on the page is BBH, 86% to 21.9%.
BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.
Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.
| Benchmark | DeepSeek V3.2 (Thinking) | Gemma 4 E2B |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | 71% | — |
| BrowseComp | 70% | — |
| OSWorld-Verified | 67% | — |
| DeepPlanning | 27.4% | — |
| CodingDeepSeek V3.2 (Thinking) wins | ||
| HumanEval | 79% | — |
| SWE-bench Verified | 48% | — |
| LiveCodeBench | 45% | 44% |
| SWE-bench Pro | 58% | — |
| Multimodal & GroundedDeepSeek V3.2 (Thinking) wins | ||
| MMMU-Pro | 66% | 44.2% |
| ReasoningDeepSeek V3.2 (Thinking) wins | ||
| MuSR | 81% | — |
| BBH | 86% | 21.9% |
| LongBench v2 | 78% | — |
| MRCRv2 | 78% | 19.1% |
| ARC-AGI-2 | 4% | — |
| KnowledgeDeepSeek V3.2 (Thinking) wins | ||
| MMLU | 87% | — |
| GPQA | 85% | 43.4% |
| SuperGPQA | 83% | — |
| MMLU-Pro | 73% | 60% |
| HLE | 22% | — |
| FrontierScience | 77% | — |
| SimpleQA | 83% | — |
| Instruction Following | ||
| IFEval | 85% | — |
| Multilingual | ||
| MGSM | 84% | — |
| MMLU-ProX | 79% | — |
| Mathematics | ||
| AIME 2023 | 87% | — |
| AIME 2024 | 89% | — |
| AIME 2025 | 88% | — |
| HMMT Feb 2023 | 83% | — |
| HMMT Feb 2024 | 85% | — |
| HMMT Feb 2025 | 84% | — |
| BRUMO 2025 | 86% | — |
| MATH-500 | 84% | — |
DeepSeek V3.2 (Thinking) is ahead overall, 67 to 39. The biggest single separator in this matchup is BBH, where the scores are 86% and 21.9%.
DeepSeek V3.2 (Thinking) has the edge for knowledge tasks in this comparison, averaging 65.9 versus 54.1. Inside this category, GPQA is the benchmark that creates the most daylight between them.
DeepSeek V3.2 (Thinking) has the edge for coding in this comparison, averaging 50.7 versus 44. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
DeepSeek V3.2 (Thinking) has the edge for reasoning in this comparison, averaging 60.1 versus 19.1. Inside this category, BBH is the benchmark that creates the most daylight between them.
DeepSeek V3.2 (Thinking) has the edge for multimodal and grounded tasks in this comparison, averaging 66 versus 44.2. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.