Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-4 Turbo
47
1/8 categoriesQwen3.5-122B-A10B
71
Winner · 6/8 categoriesGPT-4 Turbo· Qwen3.5-122B-A10B
Pick Qwen3.5-122B-A10B if you want the stronger benchmark profile. GPT-4 Turbo only becomes the better choice if reasoning is the priority or 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 47. 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 15.4. The single biggest benchmark swing on the page is SWE-bench Verified, 5% to 72%. GPT-4 Turbo does hit back in reasoning, so the answer changes if that is the part of the workload you care about most.
Qwen3.5-122B-A10B is the reasoning model in the pair, while GPT-4 Turbo 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-4 Turbo.
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-4 Turbo | Qwen3.5-122B-A10B |
|---|---|---|
| AgenticQwen3.5-122B-A10B wins | ||
| Terminal-Bench 2.0 | 42% | 49.4% |
| BrowseComp | 54% | 63.8% |
| OSWorld-Verified | 41% | 58% |
| tau2-bench | — | 79.5% |
| CodingQwen3.5-122B-A10B wins | ||
| HumanEval | 52% | — |
| SWE-bench Verified | 5% | 72% |
| LiveCodeBench | 23% | 78.9% |
| SWE-bench Pro | 14% | — |
| Multimodal & GroundedQwen3.5-122B-A10B wins | ||
| MMMU-Pro | 53% | 76.9% |
| OfficeQA Pro | 58% | — |
| ReasoningGPT-4 Turbo wins | ||
| MuSR | 56% | — |
| BBH | 75% | — |
| LongBench v2 | 62% | 60.2% |
| MRCRv2 | 62% | — |
| KnowledgeQwen3.5-122B-A10B wins | ||
| MMLU | 60% | — |
| GPQA | 60% | 86.6% |
| SuperGPQA | 58% | 67.1% |
| MMLU-Pro | 51% | 86.7% |
| FrontierScience | 52% | — |
| SimpleQA | 58% | — |
| Instruction FollowingQwen3.5-122B-A10B wins | ||
| IFEval | 80% | 93.4% |
| MultilingualQwen3.5-122B-A10B wins | ||
| MMLU-ProX | 65% | 82.2% |
| Mathematics | ||
| AIME 2023 | 60% | — |
| AIME 2024 | 62% | — |
| AIME 2025 | 61% | — |
| HMMT Feb 2023 | 56% | — |
| HMMT Feb 2024 | 58% | — |
| HMMT Feb 2025 | 57% | — |
| BRUMO 2025 | 59% | — |
| MATH-500 | 71% | — |
Qwen3.5-122B-A10B is ahead overall, 71 to 47. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 5% and 72%.
Qwen3.5-122B-A10B has the edge for knowledge tasks in this comparison, averaging 81.6 versus 54.9. Inside this category, MMLU-Pro 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 15.4. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
GPT-4 Turbo has the edge for reasoning in this comparison, averaging 60.4 versus 60.2. 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 44.7. Inside this category, OSWorld-Verified 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 55.3. 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 80. 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 65. 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.