Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Nemotron Ultra 253B
48
0/8 categoriesQwen3.5-122B-A10B
71
Winner · 7/8 categoriesNemotron Ultra 253B· Qwen3.5-122B-A10B
Pick Qwen3.5-122B-A10B if you want the stronger benchmark profile. Nemotron Ultra 253B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
Qwen3.5-122B-A10B is clearly ahead on the aggregate, 71 to 48. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen3.5-122B-A10B's sharpest advantage is in coding, where it averages 76.3 against 33.3. The single biggest benchmark swing on the page is LiveCodeBench, 30% to 78.9%.
Qwen3.5-122B-A10B gives you the larger context window at 262K, compared with 32K for Nemotron Ultra 253B.
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 | Nemotron Ultra 253B | Qwen3.5-122B-A10B |
|---|---|---|
| AgenticQwen3.5-122B-A10B wins | ||
| Terminal-Bench 2.0 | 46% | 49.4% |
| BrowseComp | 50% | 63.8% |
| OSWorld-Verified | 45% | 58% |
| tau2-bench | — | 79.5% |
| CodingQwen3.5-122B-A10B wins | ||
| HumanEval | 41% | — |
| SWE-bench Verified | 31% | 72% |
| LiveCodeBench | 30% | 78.9% |
| SWE-bench Pro | 38% | — |
| Multimodal & GroundedQwen3.5-122B-A10B wins | ||
| MMMU-Pro | 37% | 76.9% |
| OfficeQA Pro | 54% | — |
| ReasoningQwen3.5-122B-A10B wins | ||
| MuSR | 45% | — |
| BBH | 77% | — |
| LongBench v2 | 55% | 60.2% |
| MRCRv2 | 56% | — |
| KnowledgeQwen3.5-122B-A10B wins | ||
| MMLU | 49% | — |
| GPQA | 48% | 86.6% |
| SuperGPQA | 46% | 67.1% |
| MMLU-Pro | 63% | 86.7% |
| HLE | 11% | — |
| FrontierScience | 49% | — |
| SimpleQA | 47% | — |
| Instruction FollowingQwen3.5-122B-A10B wins | ||
| IFEval | 78% | 93.4% |
| MultilingualQwen3.5-122B-A10B wins | ||
| MGSM | 74% | — |
| MMLU-ProX | 68% | 82.2% |
| Mathematics | ||
| AIME 2023 | 49% | — |
| AIME 2024 | 51% | — |
| AIME 2025 | 50% | — |
| HMMT Feb 2023 | 45% | — |
| HMMT Feb 2024 | 47% | — |
| HMMT Feb 2025 | 46% | — |
| BRUMO 2025 | 48% | — |
| MATH-500 | 74% | — |
Qwen3.5-122B-A10B is ahead overall, 71 to 48. The biggest single separator in this matchup is LiveCodeBench, where the scores are 30% and 78.9%.
Qwen3.5-122B-A10B has the edge for knowledge tasks in this comparison, averaging 81.6 versus 42.6. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B has the edge for coding in this comparison, averaging 76.3 versus 33.3. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B has the edge for reasoning in this comparison, averaging 60.2 versus 52.7. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B has the edge for agentic tasks in this comparison, averaging 56 versus 46.7. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B has the edge for multimodal and grounded tasks in this comparison, averaging 76.9 versus 44.7. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B has the edge for instruction following in this comparison, averaging 93.4 versus 78. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B has the edge for multilingual tasks in this comparison, averaging 82.2 versus 70.1. Inside this category, MMLU-ProX 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.