Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Grok 4.1
91
Winner · 3/8 categoriesQwen3.5-122B-A10B
71
0/8 categoriesGrok 4.1· Qwen3.5-122B-A10B
Pick Grok 4.1 if you want the stronger benchmark profile. Qwen3.5-122B-A10B only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.
Grok 4.1 is clearly ahead on the aggregate, 91 to 71. 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 reasoning, where it averages 93 against 60.2. The single biggest benchmark swing on the page is SuperGPQA, 95% to 67.1%.
Grok 4.1 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.5-122B-A10B. That is roughly Infinityx on output cost alone. Qwen3.5-122B-A10B is the reasoning model in the pair, while Grok 4.1 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. Grok 4.1 gives you the larger context window at 1M, compared with 262K for Qwen3.5-122B-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 | Qwen3.5-122B-A10B |
|---|---|---|
| AgenticGrok 4.1 wins | ||
| BrowseComp | 84% | 63.8% |
| Terminal-Bench 2.0 | — | 49.4% |
| OSWorld-Verified | — | 58% |
| tau2-bench | — | 79.5% |
| Coding | ||
| SWE-bench Verified | — | 72% |
| LiveCodeBench | — | 78.9% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 76.9% |
| ReasoningGrok 4.1 wins | ||
| MuSR | 93% | — |
| LongBench v2 | — | 60.2% |
| KnowledgeGrok 4.1 wins | ||
| MMLU | 99% | — |
| GPQA | 97% | 86.6% |
| SuperGPQA | 95% | 67.1% |
| FrontierScience | 91% | — |
| SimpleQA | 95% | — |
| MMLU-Pro | — | 86.7% |
| Instruction Following | ||
| IFEval | — | 93.4% |
| Multilingual | ||
| MMLU-ProX | — | 82.2% |
| 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 71. The biggest single separator in this matchup is SuperGPQA, where the scores are 95% and 67.1%.
Grok 4.1 has the edge for knowledge tasks in this comparison, averaging 94.1 versus 81.6. Inside this category, SuperGPQA is the benchmark that creates the most daylight between them.
Grok 4.1 has the edge for reasoning in this comparison, averaging 93 versus 60.2. Qwen3.5-122B-A10B stays close enough that the answer can still flip depending on your workload.
Grok 4.1 has the edge for agentic tasks in this comparison, averaging 84 versus 56. Inside this category, BrowseComp 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.