Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-4o mini
55
0/8 categoriesQwen3.5-122B-A10B
71
Winner · 6/8 categoriesGPT-4o mini· Qwen3.5-122B-A10B
Pick Qwen3.5-122B-A10B if you want the stronger benchmark profile. GPT-4o mini only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
Qwen3.5-122B-A10B is clearly ahead on the aggregate, 71 to 55. 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 knowledge, where it averages 81.6 against 62. The single biggest benchmark swing on the page is BrowseComp, 49% to 63.8%.
GPT-4o mini is also the more expensive model on tokens at $0.15 input / $0.60 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 GPT-4o mini 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. Qwen3.5-122B-A10B gives you the larger context window at 262K, compared with 128K for GPT-4o mini.
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-4o mini | Qwen3.5-122B-A10B |
|---|---|---|
| AgenticQwen3.5-122B-A10B wins | ||
| Terminal-Bench 2.0 | 58% | 49.4% |
| BrowseComp | 49% | 63.8% |
| OSWorld-Verified | 44% | 58% |
| tau2-bench | — | 79.5% |
| CodingQwen3.5-122B-A10B wins | ||
| HumanEval | 87.2% | — |
| SWE-bench Pro | 65% | — |
| SWE-bench Verified | — | 72% |
| LiveCodeBench | — | 78.9% |
| Multimodal & GroundedQwen3.5-122B-A10B wins | ||
| MMMU-Pro | 66% | 76.9% |
| OfficeQA Pro | 53% | — |
| ReasoningQwen3.5-122B-A10B wins | ||
| LongBench v2 | 49% | 60.2% |
| MRCRv2 | 50% | — |
| KnowledgeQwen3.5-122B-A10B wins | ||
| MMLU | 82% | — |
| FrontierScience | 62% | — |
| MMLU-Pro | — | 86.7% |
| SuperGPQA | — | 67.1% |
| GPQA | — | 86.6% |
| Instruction Following | ||
| IFEval | — | 93.4% |
| MultilingualQwen3.5-122B-A10B wins | ||
| MGSM | 87% | — |
| MMLU-ProX | 68% | 82.2% |
| Mathematics | ||
| Coming soon | ||
Qwen3.5-122B-A10B is ahead overall, 71 to 55. The biggest single separator in this matchup is BrowseComp, where the scores are 49% and 63.8%.
Qwen3.5-122B-A10B has the edge for knowledge tasks in this comparison, averaging 81.6 versus 62. GPT-4o mini stays close enough that the answer can still flip depending on your workload.
Qwen3.5-122B-A10B has the edge for coding in this comparison, averaging 76.3 versus 65. GPT-4o mini stays close enough that the answer can still flip depending on your workload.
Qwen3.5-122B-A10B has the edge for reasoning in this comparison, averaging 60.2 versus 49.5. 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 50.9. 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 60.2. Inside this category, MMMU-Pro 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 74.7. 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.