Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Grok 4.1
91
Winner · 1/8 categoriesHolo3-122B-A10B
~79
0/8 categoriesGrok 4.1· Holo3-122B-A10B
Pick Grok 4.1 if you want the stronger benchmark profile. Holo3-122B-A10B only becomes the better choice if you want the cheaper token bill.
Grok 4.1 is clearly ahead on the aggregate, 91 to 79. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Grok 4.1's sharpest advantage is in agentic, where it averages 84 against 78.9.
Grok 4.1 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $0.40 input / $3.00 output per 1M tokens for Holo3-122B-A10B. That is roughly 5.0x on output cost alone. Grok 4.1 gives you the larger context window at 1M, 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 | Grok 4.1 | Holo3-122B-A10B |
|---|---|---|
| AgenticGrok 4.1 wins | ||
| BrowseComp | 84% | — |
| OSWorld-Verified | — | 78.8% |
| Coding | ||
| Coming soon | ||
| Multimodal & Grounded | ||
| Coming soon | ||
| Reasoning | ||
| MuSR | 93% | — |
| Knowledge | ||
| MMLU | 99% | — |
| GPQA | 97% | — |
| SuperGPQA | 95% | — |
| FrontierScience | 91% | — |
| SimpleQA | 95% | — |
| Instruction Following | ||
| Coming soon | ||
| Multilingual | ||
| Coming soon | ||
| 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% | — |
Grok 4.1 is ahead overall, 91 to 79.
Grok 4.1 has the edge for agentic tasks in this comparison, averaging 84 versus 78.9. Holo3-122B-A10B stays close enough that the answer can still flip depending on your workload.
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.