Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemini 3 Pro Deep Think
80
Winner · 0/8 categoriesHolo3-122B-A10B
~79
1/8 categoriesGemini 3 Pro Deep Think· Holo3-122B-A10B
Pick Gemini 3 Pro Deep Think if you want the stronger benchmark profile. Holo3-122B-A10B only becomes the better choice if agentic is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Gemini 3 Pro Deep Think finishes one point ahead overall, 80 to 79. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
Gemini 3 Pro Deep Think is the reasoning model in the pair, while Holo3-122B-A10B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Gemini 3 Pro Deep Think gives you the larger context window at 2M, compared with 64K for Holo3-122B-A10B.
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 | Gemini 3 Pro Deep Think | Holo3-122B-A10B |
|---|---|---|
| AgenticHolo3-122B-A10B wins | ||
| Terminal-Bench 2.0 | 77% | — |
| BrowseComp | 87% | — |
| OSWorld-Verified | 73% | 78.8% |
| Coding | ||
| HumanEval | 91% | — |
| SWE-bench Verified | 58% | — |
| LiveCodeBench | 58% | — |
| SWE-bench Pro | 63% | — |
| Multimodal & Grounded | ||
| MMMU-Pro | 95% | — |
| OfficeQA Pro | 95% | — |
| Reasoning | ||
| MuSR | 93% | — |
| BBH | 95% | — |
| LongBench v2 | 94% | — |
| MRCRv2 | 96% | — |
| ARC-AGI-2 | 45.1% | — |
| Knowledge | ||
| MMLU | 99% | — |
| GPQA | 97% | — |
| SuperGPQA | 95% | — |
| MMLU-Pro | 81% | — |
| HLE | 32% | — |
| FrontierScience | 88% | — |
| SimpleQA | 95% | — |
| Instruction Following | ||
| IFEval | 89% | — |
| Multilingual | ||
| MGSM | 92% | — |
| MMLU-ProX | 85% | — |
| Mathematics | ||
| AIME 2023 | 99% | — |
| AIME 2024 | 99% | — |
| AIME 2025 | 98% | — |
| HMMT Feb 2023 | 95% | — |
| HMMT Feb 2024 | 97% | — |
| HMMT Feb 2025 | 96% | — |
| BRUMO 2025 | 96% | — |
| MATH-500 | 92% | — |
Gemini 3 Pro Deep Think is ahead overall, 80 to 79. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 73% and 78.8%.
Holo3-122B-A10B has the edge for agentic tasks in this comparison, averaging 78.9 versus 78.1. Inside this category, OSWorld-Verified 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.