Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-5.1
78
0/8 categoriesHolo3-122B-A10B
~79
Winner · 1/8 categoriesGPT-5.1· Holo3-122B-A10B
Pick Holo3-122B-A10B if you want the stronger benchmark profile. GPT-5.1 only becomes the better choice if you need the larger 200K context window or you want the stronger reasoning-first profile.
Holo3-122B-A10B finishes one point ahead overall, 79 to 78. 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.
Holo3-122B-A10B's sharpest advantage is in agentic, where it averages 78.9 against 75.8. The single biggest benchmark swing on the page is OSWorld-Verified, 71% to 78.8%.
GPT-5.1 is also the more expensive model on tokens at $1.50 input / $6.00 output per 1M tokens, versus $0.40 input / $3.00 output per 1M tokens for Holo3-122B-A10B. That is roughly 2.0x on output cost alone. GPT-5.1 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. GPT-5.1 gives you the larger context window at 200K, 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 | GPT-5.1 | Holo3-122B-A10B |
|---|---|---|
| AgenticHolo3-122B-A10B wins | ||
| Terminal-Bench 2.0 | 78% | — |
| BrowseComp | 79% | — |
| OSWorld-Verified | 71% | 78.8% |
| Coding | ||
| HumanEval | 89% | — |
| SWE-bench Verified | 68% | — |
| LiveCodeBench | 61% | — |
| SWE-bench Pro | 71% | — |
| Multimodal & Grounded | ||
| MMMU-Pro | 94% | — |
| OfficeQA Pro | 89% | — |
| Reasoning | ||
| MuSR | 91% | — |
| BBH | 92% | — |
| LongBench v2 | 84% | — |
| MRCRv2 | 84% | — |
| ARC-AGI-2 | 17.6% | — |
| Knowledge | ||
| MMLU | 97% | — |
| GPQA | 95% | — |
| SuperGPQA | 93% | — |
| MMLU-Pro | 83% | — |
| HLE | 27% | — |
| FrontierScience | 84% | — |
| SimpleQA | 93% | — |
| Instruction Following | ||
| IFEval | 89% | — |
| Multilingual | ||
| MGSM | 89% | — |
| MMLU-ProX | 87% | — |
| 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 | 94% | — |
Holo3-122B-A10B is ahead overall, 79 to 78. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 71% and 78.8%.
Holo3-122B-A10B has the edge for agentic tasks in this comparison, averaging 78.9 versus 75.8. 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.